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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 32931
    Prev
    Next
    INDEX
    Explanations

    text indicating replies to emails and technical details

    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    565
    +0.05
    0.5%
    481
    +0.05
    0.5%
    119
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.05
    0.39
    64
    +0.05
    -0.21
    6
    +0.05
    0.18
    Negative Logits
    interstitial
    -0.41
    uph
    -0.32
    ithmetic
    -0.31
    alore
    -0.30
    urat
    -0.30
    emis
    -0.29
    aer
    -0.29
    tain
    -0.29
     recognise
    -0.28
    warts
    -0.28
    POSITIVE LOGITS
    _>
    0.38
     -----
    0.32
    ITED
    0.32
    ··
    0.30
    ________________________________
    0.29
    ONG
    0.29
     Buffett
    0.28
     Crosby
    0.28
    Commerce
    0.27
    ________________________
    0.27
    Activations Density 9.678%

    No Known Activations