© 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. 10-RES-JB
    11. 9915
    Prev
    Next
    INDEX
    Explanations

    keywords related to different media platforms and websites

    oai_token-act-pair · gpt-3.5-turbo

    mentions of media platforms and promotional content related to sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dame
    -0.66
     repr
    -0.65
     bun
    -0.64
    etts
    -0.64
    naires
    -0.63
     Claus
    -0.61
     Borders
    -0.61
    runs
    -0.59
     Bridges
    -0.59
     appar
    -0.58
    POSITIVE LOGITS
    Dad
    0.81
    TOP
    0.80
    Inside
    0.79
    Magazine
    0.77
    Daily
    0.77
    shock
    0.74
    Month
    0.74
    Sport
    0.71
    Movie
    0.70
    Complete
    0.70
    Activations Density 0.128%

    No Known Activations