© 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 EvalsExportsAPI 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. 7-RES-JB
    11. 24048
    Prev
    Next
    INDEX
    Explanations

    mentions of different states and territories within the United States

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations, specifically states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rious
    -0.68
    bor
    -0.68
    erb
    -0.67
    efficiency
    -0.65
    Ry
    -0.65
    rag
    -0.64
    gener
    -0.62
    hod
    -0.62
    Mill
    -0.62
    antry
    -0.61
    POSITIVE LOGITS
     apiece
    0.95
     including
    0.91
     totaling
    0.85
     vying
    0.83
     nationwide
    0.80
     spanning
    0.79
     worldwide
    0.77
     Including
    0.75
    essee
    0.69
     consecut
    0.69
    Activations Density 0.194%

    No Known Activations