© 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. 36424
    Prev
    Next
    INDEX
    Explanations

    technical terms related to information technology and internet networking

    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
    71
    +0.08
    0.5%
    634
    +0.07
    0.4%
    656
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.08
    0.21
    267
    +0.07
    0.12
    6
    +0.07
    0.14
    Negative Logits
    ded
    -0.58
    yll
    -0.52
     losers
    -0.51
    200000
    -0.51
     resc
    -0.49
     retri
    -0.48
    emer
    -0.47
    ":["
    -0.46
     insepar
    -0.46
    Ö¼
    -0.46
    POSITIVE LOGITS
     Theatre
    0.62
     Interview
    0.56
    Exit
    0.55
    Disney
    0.53
     Talks
    0.52
     Yards
    0.51
    Pic
    0.50
    Interview
    0.50
     Screen
    0.49
     VIDEOS
    0.49
    Activations Density 4.901%

    No Known Activations