© 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. 1260
    Prev
    Next
    INDEX
    Explanations

    references to religious beliefs, especially related to the Jehovah's Witnesses, and UFO sightings and related conspiracy theories

    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
    57
    +0.13
    0.5%
    84
    +0.12
    0.5%
    336
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.15
    326
    +0.12
    0.11
    57
    +0.11
    0.07
    Negative Logits
    ioned
    -0.92
    rations
    -0.92
    RNA
    -0.80
    phrine
    -0.80
    disk
    -0.80
    lan
    -0.77
    amina
    -0.76
    ration
    -0.76
    comed
    -0.75
    ammy
    -0.75
    POSITIVE LOGITS
    CLASSIFIED
    0.76
    SourceFile
    0.70
    PDATE
    0.70
    querque
    0.67
     Eclipse
    0.67
    ileaks
    0.67
    ÃįÃį
    0.66
     mosqu
    0.65
    alkyrie
    0.65
    £ı
    0.64
    Activations Density 1.749%

    No Known Activations