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

    Neuronpedia

    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. 10-RES-JB
    11. 8612
    Prev
    Next
    INDEX
    Explanations

    organizations, committees, and associations related to politics

    oai_token-act-pair · gpt-3.5-turbo

    references to political organizations and committees

    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
    range
    -0.79
    ...]
    -0.77
    microsoft
    -0.72
    roma
    -0.72
    google
    -0.71
    wcsstore
    -0.68
    liga
    -0.67
    genre
    -0.67
    udeau
    -0.65
    sci
    -0.65
    POSITIVE LOGITS
     Chairman
    1.17
     Chair
    1.10
     officials
    1.05
     member
    1.01
     members
    1.00
     spokesman
    0.97
     chairman
    0.94
     deputy
    0.92
     spokeswoman
    0.91
     staffers
    0.91
    Activations Density 0.284%

    No Known Activations