© 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. 35915
    Prev
    Next
    INDEX
    Explanations

    information related to sports players and their performances and evaluations

    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
    +0.37
    1.7%
    175
    +0.09
    0.4%
    481
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    130
    +0.37
    0.06
    160
    +0.09
    0.26
    255
    +0.09
    0.14
    Negative Logits
    olulu
    -0.74
     oneself
    -0.73
    azard
    -0.69
    amiya
    -0.63
     ourselves
    -0.61
    Spawn
    -0.58
    orks
    -0.58
    pez
    -0.57
     Byr
    -0.57
    ievers
    -0.57
    POSITIVE LOGITS
     consisted
    0.92
     consists
    0.89
     differs
    0.85
     woes
    0.78
     revolves
    0.78
     spans
    0.76
     extends
    0.74
    mates
    0.72
     encompasses
    0.72
     sucks
    0.72
    Activations Density 22.119%

    No Known Activations