© 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. 12577
    Prev
    Next
    INDEX
    Explanations

    proper nouns relating to various topics such as politics, literature, and sports

    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
    556
    +0.21
    0.6%
    659
    +0.18
    0.5%
    284
    +0.18
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.21
    0.08
    556
    +0.18
    0.07
    701
    +0.18
    0.05
    Negative Logits
     Cosponsors
    -1.16
    ongyang
    -1.10
    hift
    -1.08
     Gutenberg
    -1.00
    =-=-
    -0.98
    sels
    -0.95
    nesday
    -0.94
    conserv
    -0.94
    =-=-=-=-
    -0.93
     ILCS
    -0.92
    POSITIVE LOGITS
    azeera
    1.51
    querque
    1.28
    hyde
    1.27
    arez
    1.20
    awi
    1.19
    ida
    1.15
    aeda
    1.12
    dash
    1.09
     Lama
    1.09
    way
    1.08
    Activations Density 1.365%

    No Known Activations