© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 21028
    Prev
    Next
    INDEX
    Explanations

    decisive actions or impactful statements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to claims, decisions, and allegations in a context of actions or accusations

    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
    .:
    -0.72
    iries
    -0.72
    .;
    -0.66
    ubes
    -0.64
    aru
    -0.63
     actionGroup
    -0.62
     Volunte
    -0.62
    ixties
    -0.62
    addons
    -0.61
    build
    -0.60
    POSITIVE LOGITS
     echoed
    1.06
     unheard
    0.98
     which
    0.94
     reminiscent
    0.94
     exacerbated
    0.92
     that
    0.86
     sorely
    0.85
     reiterated
    0.82
     unthinkable
    0.80
     bolstered
    0.80
    Activations Density 0.211%

    No Known Activations