© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3927
    Prev
    Next
    INDEX
    Explanations

    information related to features, settings, and configurations that can be adjusted or optimized to achieve a specific desired outcome

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    719
    +0.09
    0.4%
    329
    +0.09
    0.4%
    177
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.09
    0.14
    472
    +0.09
    0.06
    479
    +0.09
    0.03
    Negative Logits
    lua
    -0.75
    rics
    -0.74
    sheets
    -0.72
    ols
    -0.70
    alos
    -0.70
    alon
    -0.70
    hens
    -0.70
    sheet
    -0.69
    pan
    -0.69
    acus
    -0.69
    POSITIVE LOGITS
     Parenthood
    0.86
     outcome
    0.83
     destination
    0.81
     outcomes
    0.79
     sender
    0.75
     destinations
    0.74
     targets
    0.70
     embodiments
    0.70
     recipient
    0.70
     behaviour
    0.69
    Activations Density 6.570%

    No Known Activations