© 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. 0-RES-JB
    11. 11625
    Prev
    Next
    INDEX
    Explanations

    mentions of sharing or spreading content online

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Share" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ``
    -0.73
     prec
    -0.71
     quart
    -0.71
     aud
    -0.69
     gate
    -0.68
     heav
    -0.67
     pert
    -0.66
     naive
    -0.66
     introductory
    -0.66
     experimental
    -0.66
    POSITIVE LOGITS
    Share
    4.00
    share
    2.04
     Share
    1.91
    SHARE
    1.88
    Advertisements
    1.55
    Shares
    1.54
    Spread
    1.36
    sharing
    1.30
    Tweet
    1.28
     share
    1.27
    Activations Density 0.016%

    No Known Activations