© 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. 13342
    Prev
    Next
    INDEX
    Explanations

    text related to distressing events or emergencies

    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
    259
    +0.14
    0.5%
    762
    +0.14
    0.5%
    233
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.04
    760
    +0.14
    0.04
    570
    +0.12
    0.02
    Negative Logits
    itness
    -0.97
    RIP
    -0.96
    ATURE
    -0.95
    uyomi
    -0.92
    ema
    -0.87
    ĸļ
    -0.87
    estones
    -0.86
    utenberg
    -0.85
    orescent
    -0.85
    estone
    -0.84
    POSITIVE LOGITS
     etc
    0.90
    avascript
    0.84
    ttes
    0.79
    âĢ¦]
    0.77
     Luo
    0.75
    mong
    0.74
     âĢ¦"
    0.72
    lite
    0.71
     CPC
    0.70
    âĢ¦"
    0.70
    Activations Density 0.668%

    No Known Activations