© 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. 10997
    Prev
    Next
    INDEX
    Explanations

    mentions of same-sex marriage, related legal proceedings, and personal views on the topic

    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
    19
    +0.18
    0.6%
    378
    +0.17
    0.6%
    242
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.18
    0.05
    124
    +0.17
    0.04
    425
    +0.14
    0.04
    Negative Logits
     "$:/
    -0.96
     IPM
    -0.95
     Sawyer
    -0.92
    LIB
    -0.91
    jri
    -0.91
    enegger
    -0.90
     enthusi
    -0.87
     Xer
    -0.87
     mathemat
    -0.86
     Tul
    -0.86
    POSITIVE LOGITS
    chance
    1.18
    origin
    1.16
    worldly
    1.08
    sized
    1.08
    sex
    1.07
    legged
    1.06
    Origin
    1.05
    bodied
    1.04
    sided
    1.04
    majority
    1.03
    Activations Density 0.317%

    No Known Activations