© 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. 10246
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific events or actions, such as 'search' or 'playoff run'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to competitive scenarios and events

    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
    iates
    -0.68
    urus
    -0.68
    amples
    -0.67
    nor
    -0.65
    forts
    -0.65
    events
    -0.63
     booths
    -0.63
    Trivia
    -0.62
     Guides
    -0.62
    ooks
    -0.62
    POSITIVE LOGITS
     spanning
    1.21
     riddled
    1.13
     overseen
    1.12
     headlined
    1.11
     reminiscent
    1.11
     that
    1.08
     rife
    1.08
     fraught
    1.05
     spearheaded
    1.05
     dominated
    1.05
    Activations Density 0.426%

    No Known Activations