© 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. 0-RES-JB
    11. 20087
    Prev
    Next
    INDEX
    Explanations

    references to local government and events in a specific locality

    oai_token-act-pair · gpt-3.5-turbo

    references to local government or local organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plateau
    -0.73
     mant
    -0.73
     tou
    -0.69
    antz
    -0.68
     pens
    -0.67
     payoff
    -0.66
     yielding
    -0.65
     bow
    -0.65
     pudding
    -0.65
     conce
    -0.64
    POSITIVE LOGITS
     Local
    3.76
    Local
    2.87
    local
    2.19
     local
    1.94
     locals
    1.69
     locally
    1.53
     Loc
    1.51
     Regional
    1.46
     LOC
    1.44
    Loc
    1.34
    Activations Density 0.013%

    No Known Activations