© 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. 31300
    Prev
    Next
    INDEX
    Explanations

    names, especially of people and locations

    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
    396
    +0.12
    0.5%
    29
    +0.11
    0.5%
    659
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.20
    232
    +0.11
    0.15
    326
    +0.10
    0.17
    Negative Logits
    ¥µ
    -0.72
    igators
    -0.70
    direction
    -0.69
    OWER
    -0.67
    AppData
    -0.66
    igator
    -0.66
    limits
    -0.66
     uter
    -0.65
    odiac
    -0.65
    exempt
    -0.65
    POSITIVE LOGITS
     Robinson
    1.09
     McCull
    1.03
     McC
    1.02
     Reed
    1.02
     Richards
    1.02
     McInt
    1.02
     McKay
    1.01
     Larson
    1.00
     Farrell
    1.00
     Michaels
    0.99
    Activations Density 6.168%

    No Known Activations