© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2163
    Prev
    Next
    INDEX
    Explanations

    HTML elements related to photos and captions in news articles

    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
    746
    +0.18
    0.7%
    240
    +0.11
    0.4%
    274
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.18
    -0.00
    387
    +0.11
    0.01
    587
    +0.11
    0.01
    Negative Logits
     Drake
    -0.90
     Cole
    -0.87
     Cantor
    -0.86
     Hardy
    -0.82
    scribe
    -0.81
    fol
    -0.81
     Benz
    -0.81
    weed
    -0.80
    EGA
    -0.80
    olester
    -0.80
    POSITIVE LOGITS
     Created
    1.02
     Shutdown
    1.01
     Sketch
    0.99
    idth
    0.95
    CLASSIFIED
    0.93
    hran
    0.88
    ãĥķ
    0.86
    pmwiki
    0.85
    Gallery
    0.84
    ://
    0.82
    Activations Density 0.016%

    No Known Activations