© 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
    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. 1000
    Prev
    Next
    INDEX
    Explanations

    the word "Capitol"

    oai_token-act-pair · gpt-4-turbo

    references to a specific location, specifically "Capitol."

    oai_token-act-pair · gpt-3.5-turbo

    references to the Capitol building or related political contexts

    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
    gger
    -0.81
    ãģ¦
    -0.75
     Bucc
    -0.72
    hari
    -0.71
    earch
    -0.70
    err
    -0.68
    words
    -0.66
    facts
    -0.65
    Episode
    -0.65
    %%%%
    -0.65
    POSITIVE LOGITS
    itol
    1.19
     Capitol
    1.03
     Hill
    0.94
    rament
    0.83
     dome
    0.79
     lobbying
    0.73
     entrances
    0.73
    ratulations
    0.72
     sten
    0.71
     Heights
    0.71
    Activations Density 0.015%

    No Known Activations