© 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
    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. 35430
    Prev
    Next
    INDEX
    Explanations

    proper nouns and locations

    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
    106
    +0.11
    0.6%
    285
    +0.10
    0.5%
    119
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    285
    +0.11
    0.05
    106
    +0.10
    0.09
    326
    +0.10
    0.21
    Negative Logits
    lished
    -0.76
    oÄŁ
    -0.71
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.69
    è¦ļéĨĴ
    -0.67
    é¾įå¥ij士
    -0.63
    aptic
    -0.62
    =-=-=-=-=-=-=-=-
    -0.62
     BaseType
    -0.61
    blance
    -0.60
    lich
    -0.60
    POSITIVE LOGITS
    ibrary
    1.06
    usions
    0.93
    ustration
    0.89
    uminati
    0.88
    vl
    0.86
    usive
    0.86
    umin
    0.85
    usion
    0.81
    iter
    0.78
    angelo
    0.77
    Activations Density 7.683%

    No Known Activations