© 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. 3006
    Prev
    Next
    INDEX
    Explanations

    mentions related to political conflicts and social injustices

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    744
    +0.19
    0.6%
    370
    +0.14
    0.4%
    394
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    598
    +0.19
    0.06
    240
    +0.14
    0.06
    744
    +0.14
    0.06
    Negative Logits
    xual
    -1.00
    idon
    -0.93
    emies
    -0.89
    Ò
    -0.89
     Heist
    -0.87
    swick
    -0.85
     Hollow
    -0.84
    ¶
    -0.84
    cases
    -0.84
    enary
    -0.83
    POSITIVE LOGITS
    bered
    1.21
    othe
    1.11
    ooo
    1.05
    ament
    1.04
    arer
    1.01
     much
    1.01
    ARE
    0.99
    oooo
    0.98
     unsurprisingly
    0.97
    apy
    0.97
    Activations Density 0.873%

    No Known Activations