© 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. 10248
    Prev
    Next
    INDEX
    Explanations

    phrases related to upgrading or updating services or subscriptions

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to subscription upgrades and notifications

    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
    abouts
    -0.62
    nesses
    -0.58
    olina
    -0.56
    ppings
    -0.55
    stem
    -0.53
    enium
    -0.53
     bount
    -0.53
    eteenth
    -0.53
    paces
    -0.52
     Doe
    -0.52
    POSITIVE LOGITS
     YOUR
    0.67
     Your
    0.63
     your
    0.61
    iframe
    0.56
    Your
    0.56
    SK
    0.56
    iao
    0.55
    ROR
    0.55
    icro
    0.55
    dayName
    0.54
    Activations Density 0.015%

    No Known Activations