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

    Neuronpedia

    Jacobian LensNEW
    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. 33402
    Prev
    Next
    INDEX
    Explanations

    mentions of personal experiences and opinions

    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
    447
    +0.19
    0.9%
    763
    +0.12
    0.6%
    142
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.19
    0.13
    119
    +0.12
    0.12
    64
    +0.09
    -0.25
    Negative Logits
    States
    -0.61
    Britain
    -0.58
    nick
    -0.57
    behind
    -0.55
    Eastern
    -0.54
     Julius
    -0.52
    Roman
    -0.52
    Present
    -0.51
    angle
    -0.49
     denomination
    -0.49
    POSITIVE LOGITS
    rontal
    0.64
    wcsstore
    0.63
     Been
    0.61
    ãĥĨ
    0.59
    °
    0.58
    ãĤ¦ãĤ¹
    0.58
    CLASSIFIED
    0.56
    ãģ®å
    0.55
     Valkyrie
    0.55
     gone
    0.53
    Activations Density 14.142%

    No Known Activations