© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 8749
    Prev
    Next
    INDEX
    Explanations

    phrases related to political discussions and interactions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    393
    +0.30
    1.1%
    685
    +0.15
    0.5%
    380
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.30
    0.11
    100
    +0.15
    0.08
    297
    +0.13
    0.08
    Negative Logits
    adas
    -0.94
    RNA
    -0.75
     popup
    -0.75
     formation
    -0.75
     courier
    -0.74
     Cato
    -0.73
     unnecess
    -0.73
     seams
    -0.72
    Engineers
    -0.72
    formed
    -0.71
    POSITIVE LOGITS
     yeah
    1.24
     please
    1.03
     uh
    0.97
    ItemImage
    0.95
    icio
    0.91
     yes
    0.90
     moreover
    0.89
     although
    0.89
     I
    0.89
    there
    0.87
    Activations Density 1.687%

    No Known Activations