© 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. 8-RES-JB
    11. 4598
    Prev
    Next
    INDEX
    Explanations

    terms related to the federal government

    oai_token-act-pair · gpt-3.5-turbo

    references to federal government activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ktop
    -0.91
    zzo
    -0.77
    hops
    -0.74
    bler
    -0.73
    paces
    -0.72
    chains
    -0.72
    oldemort
    -0.70
    schild
    -0.70
    vier
    -0.70
    INESS
    -0.68
    POSITIVE LOGITS
     government
    1.14
     election
    0.93
     parliament
    0.93
     treasury
    0.92
     judiciary
    0.91
     NDP
    0.87
     governments
    0.87
     office
    0.85
    ised
    0.84
     Government
    0.83
    Activations Density 0.032%

    No Known Activations