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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 7771
    Prev
    Next
    INDEX
    Explanations

    key phrases related to making decisions or choices

    oai_token-act-pair · gpt-3.5-turbo

    instances of conjunctions indicating connections or agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aretz
    -0.74
    reet
    -0.69
    aw
    -0.68
    wat
    -0.67
    urion
    -0.67
    furt
    -0.64
    BAT
    -0.64
    laughter
    -0.64
    aws
    -0.63
    advertisement
    -0.63
    POSITIVE LOGITS
     replaced
    0.97
     simplify
    0.93
     thereby
    0.87
     eliminate
    0.83
     replaces
    0.83
     concentrate
    0.83
     dismantled
    0.81
     thus
    0.80
     eliminates
    0.79
     consequently
    0.78
    Activations Density 0.315%

    No Known Activations