© 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. 37085
    Prev
    Next
    INDEX
    Explanations

    political and social commentary related phrases

    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
    447
    +0.25
    1.9%
    393
    +0.18
    1.4%
    362
    +0.09
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    385
    +0.25
    0.37
    362
    +0.18
    0.32
    393
    +0.09
    0.36
    Negative Logits
     realise
    -0.42
    irtual
    -0.42
    SPONSORED
    -0.41
     directs
    -0.41
    iliate
    -0.40
    ounces
    -0.39
     partake
    -0.39
    ionics
    -0.38
    hips
    -0.38
     separately
    -0.38
    POSITIVE LOGITS
    oret
    1.02
    resa
    0.80
    atre
    0.77
    odore
    0.76
    ories
    0.71
    ory
    0.66
    ater
    0.63
    orem
    0.60
     earliest
    0.57
     biggest
    0.57
    Activations Density 8.810%

    No Known Activations