© 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. 36019
    Prev
    Next
    INDEX
    Explanations

    interrogative statements asking for additional information

    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
    +0.17
    0.9%
    271
    +0.10
    0.5%
    109
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.17
    0.25
    255
    +0.10
    0.15
    393
    +0.09
    0.29
    Negative Logits
    Runner
    -0.65
    Upload
    -0.59
     KH
    -0.59
    gets
    -0.57
     Encyclopedia
    -0.56
    gers
    -0.55
    hai
    -0.55
    haw
    -0.54
    sters
    -0.54
     Derby
    -0.54
    POSITIVE LOGITS
    worldly
    0.99
     besides
    0.82
     entirely
    0.67
     includ
    0.65
     happened
    0.63
     imaginable
    0.63
     describ
    0.62
     happens
    0.61
    nces
    0.61
     else
    0.61
    Activations Density 13.139%

    No Known Activations