© 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. 6467
    Prev
    Next
    INDEX
    Explanations

    phrases related to interrogative statements and rhetorical questions

    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
    393
    +0.26
    1.0%
    195
    +0.14
    0.5%
    629
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    126
    +0.26
    0.07
    348
    +0.14
    0.08
    263
    +0.12
    0.06
    Negative Logits
    endants
    -0.86
    enburg
    -0.83
    idon
    -0.81
    ster
    -0.78
    gu
    -0.78
    viks
    -0.77
    ñ
    -0.75
    jee
    -0.74
    ages
    -0.74
    iston
    -0.73
    POSITIVE LOGITS
     happened
    1.10
     transpired
    1.06
     happens
    1.03
     constituted
    0.93
     constitutes
    0.92
     sorts
    0.87
     kinds
    0.84
     humanity
    0.83
     exactly
    0.82
    thumbnails
    0.81
    Activations Density 1.254%

    No Known Activations