© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 3262
    Prev
    Next
    INDEX
    Explanations

    words related to sports announcers and sportscasting

    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
    51
    +0.12
    0.5%
    345
    +0.11
    0.5%
    80
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    51
    +0.12
    0.10
    229
    +0.11
    0.05
    345
    +0.10
    0.08
    Negative Logits
    iscons
    -0.80
    FTWARE
    -0.69
    Ire
    -0.67
     unpop
    -0.65
    colo
    -0.61
    Moreover
    -0.61
    dor
    -0.59
    INST
    -0.59
    Was
    -0.59
    leck
    -0.58
    POSITIVE LOGITS
     nowadays
    0.94
     ALWAYS
    0.84
     inherently
    0.83
    ateur
    0.79
     typically
    0.77
     usually
    0.74
     always
    0.73
     Journalism
    0.71
     sometimes
    0.71
     finite
    0.70
    Activations Density 8.637%

    No Known Activations