© 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. 11-RES-JB
    11. 2455
    Prev
    Next
    INDEX
    Explanations

    words related to writing and creating content

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "write" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ĭ±
    -0.76
    alon
    -0.76
    liv
    -0.74
    EGA
    -0.70
    agara
    -0.68
    arov
    -0.67
    iere
    -0.67
    ella
    -0.67
    anamo
    -0.66
    Bron
    -0.66
    POSITIVE LOGITS
     about
    1.09
     poems
    1.03
    itatively
    1.01
     essays
    0.96
     poetry
    0.95
     letters
    0.92
     down
    0.88
     checks
    0.87
     novels
    0.87
     lyrics
    0.84
    Activations Density 0.061%

    No Known Activations