© 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. 8845
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and security

    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
    393
    +0.19
    0.9%
    51
    +0.11
    0.5%
    570
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.19
    0.28
    566
    +0.11
    0.15
    570
    +0.10
    0.02
    Negative Logits
     unlaw
    -0.70
    âĢİ
    -0.68
    rament
    -0.66
    ï¸
    -0.62
    ucc
    -0.62
     philos
    -0.61
     acron
    -0.60
     Franch
    -0.60
     terminology
    -0.60
     Definitions
    -0.59
    POSITIVE LOGITS
     automatically
    0.99
     instantly
    0.90
    Interstitial
    0.86
     expend
    0.85
     subconscious
    0.84
     magically
    0.83
     thereby
    0.80
     indistinguishable
    0.79
     unconsciously
    0.79
     forfeit
    0.77
    Activations Density 10.819%

    No Known Activations