© 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. 8100
    Prev
    Next
    INDEX
    Explanations

    names related to individuals or companies (like "Strauss" and "Fox News")

    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
    326
    +0.15
    0.7%
    23
    +0.14
    0.6%
    526
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.15
    0.10
    288
    +0.14
    0.11
    659
    +0.14
    0.07
    Negative Logits
    è¦ļéĨĴ
    -0.73
     visitation
    -0.72
    gdala
    -0.71
    heid
    -0.70
     Ashton
    -0.70
    bleacher
    -0.69
    eor
    -0.69
    ICLE
    -0.66
    20439
    -0.64
    ICA
    -0.64
    POSITIVE LOGITS
    fing
    1.05
    pping
    1.03
    pped
    1.01
    eties
    0.91
    fed
    0.87
    pper
    0.84
    stra
    0.83
    ppers
    0.83
    ussian
    0.82
    moil
    0.82
    Activations Density 1.477%

    No Known Activations