© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 3719
    Prev
    Next
    INDEX
    Explanations

    information related to specific incidents or events, such as crimes, sports, or research studies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Layer 6 UMAP region: Local cluster above bottom line touching e2e-recon cluster - local

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.31
    1.9%
    640
    +0.17
    1.0%
    679
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.31
    0.33
    679
    +0.17
    0.35
    640
    +0.14
    0.35
    Negative Logits
     mosqu
    -0.67
    ·
    -0.57
    ĸ
    -0.56
    awei
    -0.56
     quir
    -0.55
     volunte
    -0.55
     unch
    -0.55
     hammered
    -0.54
    ©¶æ
    -0.54
     fermented
    -0.54
    POSITIVE LOGITS
     Especially
    0.93
     However
    0.88
     Its
    0.88
     Unfortunately
    0.85
     Fortunately
    0.84
     Specifically
    0.84
     Also
    0.84
     They
    0.81
     Additionally
    0.81
     Instead
    0.81
    Activations Density 9.180%

    No Known Activations