© 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. 10-RES-JB
    11. 9974
    Prev
    Next
    INDEX
    Explanations

    mentions of government ministries and departments

    oai_token-act-pair · gpt-3.5-turbo

    references to government ministries or departments

    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
    schild
    -0.65
     Eclipse
    -0.64
     Roosevelt
    -0.63
    avery
    -0.62
    orget
    -0.60
    vent
    -0.60
    redo
    -0.59
     Nation
    -0.59
     Karma
    -0.58
     Century
    -0.57
    POSITIVE LOGITS
    onse
    0.82
    oun
    0.81
     ministries
    0.80
     approves
    0.77
    assy
    0.76
     spokes
    0.76
    aceutical
    0.75
     apparatus
    0.73
     spokesman
    0.73
    idium
    0.73
    Activations Density 0.028%

    No Known Activations