© 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 Local
    9. 6-RES_SCL-AJT
    11. 36801
    Prev
    Next
    INDEX
    Explanations

    names related to journalists or public figures

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.27
    1.2%
    668
    +0.12
    0.5%
    53
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    46
    +0.27
    0.12
    288
    +0.12
    0.19
    547
    +0.12
    0.07
    Negative Logits
    Ire
    -0.81
    ãĤ©
    -0.76
    à¨
    -0.72
    Ir
    -0.71
    Reviewer
    -0.69
    ãĥŁ
    -0.68
    ãĤŃ
    -0.66
    Maria
    -0.66
    ãĤ¨ãĥ«
    -0.66
    ãĥ¼ãĤ¯
    -0.65
    POSITIVE LOGITS
     Jr
    1.01
    steen
    0.88
    agher
    0.87
     III
    0.83
    enstein
    0.81
    bey
    0.81
     Sr
    0.77
    zinski
    0.73
    gaard
    0.73
    hler
    0.72
    Activations Density 7.996%

    No Known Activations