© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 12770
    Prev
    Next
    INDEX
    Explanations

    names of individuals or specific entities, potentially related to politics

    oai_token-act-pair · gpt-3.5-turbo

    names and terms associated with Sinn Féin and prominent individuals related to it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arding
    -0.83
    uate
    -0.81
    orate
    -0.80
    uates
    -0.79
    umen
    -0.78
    arded
    -0.75
    iard
    -0.71
    umin
    -0.71
    yright
    -0.70
    jamin
    -0.70
    POSITIVE LOGITS
    Account
    0.84
    stice
    0.79
    Sys
    0.78
     Potato
    0.75
    eways
    0.75
     Instrument
    0.74
     Sack
    0.73
    Solid
    0.73
     Sail
    0.73
    addle
    0.73
    Activations Density 0.065%

    No Known Activations