© 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. 33264
    Prev
    Next
    INDEX
    Explanations

    words related to legal and scientific terms or concepts

    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
    655
    +0.10
    0.5%
    114
    +0.09
    0.5%
    146
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    299
    +0.10
    0.14
    406
    +0.09
    0.12
    284
    +0.09
    0.11
    Negative Logits
    ãĥ¼ãĥĨ
    -0.69
    uckland
    -0.65
     referen
    -0.58
    £ı
    -0.57
    CHAT
    -0.56
    CHR
    -0.56
    ãĥ£
    -0.56
     stump
    -0.55
    xual
    -0.54
    Chel
    -0.52
    POSITIVE LOGITS
     Phant
    0.73
    ilial
    0.61
    itious
    0.58
    agy
    0.56
    ruary
    0.55
     ATM
    0.55
    doms
    0.52
    sec
    0.51
    oms
    0.51
     Barg
    0.49
    Activations Density 9.849%

    No Known Activations