© 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. 3-RES-JB
    11. 2955
    Prev
    Next
    INDEX
    Explanations

    mentions of statewide issues or events

    oai_token-act-pair · gpt-3.5-turbo

    references to statewide policies and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    glers
    -1.06
    alid
    -0.87
    nels
    -0.85
    emis
    -0.84
    thia
    -0.83
    selage
    -0.82
    urai
    -0.79
    alus
    -0.78
    thur
    -0.77
    sels
    -0.77
    POSITIVE LOGITS
     statewide
    1.11
    wide
    0.99
     corrections
    0.80
     unemployment
    0.76
     parks
    0.76
     ballot
    0.74
     voter
    0.73
     sheriff
    0.73
    é¾įå¥ij士
    0.72
     election
    0.71
    Activations Density 0.005%

    No Known Activations