© 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 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. 12110
    Prev
    Next
    INDEX
    Explanations

    technical instructions or code snippets

    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
    640
    +0.27
    0.9%
    447
    +0.17
    0.5%
    84
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    699
    +0.27
    0.05
    108
    +0.17
    0.07
    231
    +0.16
    0.06
    Negative Logits
     darling
    -0.94
     chained
    -0.93
    imore
    -0.93
     Lutheran
    -0.90
    owment
    -0.89
    itiz
    -0.88
     contraception
    -0.86
    ppe
    -0.85
     Dickinson
    -0.84
     rhy
    -0.84
    POSITIVE LOGITS
    =-=-=-=-=-=-=-=-
    1.26
    =-=-=-=-
    1.26
     Advertisement
    1.24
     largeDownload
    1.14
    Names
    1.07
    Bul
    1.02
    mosp
    1.01
    taboola
    1.00
    Introdu
    0.99
    webkit
    0.99
    Activations Density 0.585%

    No Known Activations