© 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. 12491
    Prev
    Next
    INDEX
    Explanations

    topics related to the Catholic Church

    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
    288
    +0.29
    1.0%
    89
    +0.16
    0.6%
    566
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.29
    0.10
    267
    +0.16
    0.06
    752
    +0.14
    0.06
    Negative Logits
    utherford
    -1.17
    Downloadha
    -1.07
    rg
    -1.07
    hov
    -1.03
    inventoryQuantity
    -0.97
     Cheong
    -0.97
    draft
    -0.93
    nit
    -0.93
    anwhile
    -0.93
    obbies
    -0.92
    POSITIVE LOGITS
     Worker
    1.14
     equivalents
    1.02
    osate
    1.01
     Broadcasting
    0.99
     Connection
    0.99
     Kirin
    0.97
     Church
    0.95
     supremacist
    0.95
     Encyclopedia
    0.92
    ophile
    0.91
    Activations Density 0.765%

    No Known Activations