© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 32322
    Prev
    Next
    INDEX
    Explanations

    concepts related to academic topics and research, including arguments and discussions

    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
    +0.27
    1.3%
    393
    +0.14
    0.7%
    526
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.27
    0.29
    710
    +0.14
    0.13
    561
    +0.10
    0.10
    Negative Logits
    soDeliveryDate
    -0.73
    waters
    -0.69
    SourceFile
    -0.69
    ENCY
    -0.64
    ptives
    -0.63
    ãĥ¯ãĥ³
    -0.63
    externalActionCode
    -0.63
    TY
    -0.62
    ©¶æ¥µ
    -0.60
    displayText
    -0.60
    POSITIVE LOGITS
     behalf
    1.35
    erous
    0.94
    yx
    0.83
    site
    0.82
     topics
    0.80
    eday
    0.73
     board
    0.72
    shore
    0.72
    eworld
    0.71
    sets
    0.70
    Activations Density 13.446%

    No Known Activations