© 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. 3036
    Prev
    Next
    INDEX
    Explanations

    a variety of phrases related to storytelling, events, and actions

    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
    566
    +0.15
    0.6%
    545
    +0.14
    0.6%
    86
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    545
    +0.15
    0.06
    86
    +0.14
    0.06
    566
    +0.14
    0.06
    Negative Logits
     entirety
    -0.94
    aths
    -0.92
    obi
    -0.92
    ighth
    -0.85
    athed
    -0.84
    outer
    -0.81
    icol
    -0.81
    etry
    -0.81
    icator
    -0.80
    omb
    -0.80
    POSITIVE LOGITS
     anew
    1.25
    nings
    1.00
     behaving
    0.92
     bothering
    0.91
     PRESS
    0.91
     raining
    0.89
     af
    0.84
     screaming
    0.84
     dating
    0.83
     compuls
    0.82
    Activations Density 0.499%

    No Known Activations