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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13385
    Prev
    Next
    INDEX
    Explanations

    mentions of awards, nominations, and achievements in various fields like film, music, and literature

    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
    339
    +0.19
    0.6%
    77
    +0.14
    0.5%
    386
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    339
    +0.19
    0.04
    162
    +0.14
    0.04
    511
    +0.13
    0.04
    Negative Logits
    chy
    -1.08
    oidal
    -1.00
    bley
    -0.97
     baths
    -0.96
     scanner
    -0.96
    bleacher
    -0.94
     marching
    -0.94
     irrig
    -0.93
    ighter
    -0.92
    vor
    -0.92
    POSITIVE LOGITS
    seller
    1.25
     Practices
    1.22
     Worst
    1.21
     BaseType
    1.20
    ĺħ
    1.20
    ãĥ´
    1.11
    wick
    1.11
    iary
    1.10
    iaries
    1.07
    ãģı
    1.04
    Activations Density 0.374%

    No Known Activations