© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 7424
    Prev
    Next
    INDEX
    Explanations

    mentions of the act of writing

    oai_token-act-pair · gpt-3.5-turbo

    references to writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EGA
    -0.88
    Ĭ±
    -0.85
    rolet
    -0.83
    ega
    -0.79
    rals
    -0.73
    abe
    -0.73
    azar
    -0.71
    agara
    -0.71
    illon
    -0.67
    Afee
    -0.64
    POSITIVE LOGITS
    smanship
    0.86
     poems
    0.82
    writing
    0.80
     penned
    0.78
     notebook
    0.77
     writing
    0.76
     letters
    0.73
     poetry
    0.73
     essays
    0.71
     poem
    0.71
    Activations Density 0.026%

    No Known Activations