© 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. 8-RES-JB
    11. 17015
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "Democrats"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Democratic Party

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istic
    -0.83
    obar
    -0.82
    iful
    -0.78
    icles
    -0.77
    efully
    -0.77
     Jehovah
    -0.72
    ocity
    -0.72
    outine
    -0.71
    orical
    -0.71
    ooter
    -0.71
    POSITIVE LOGITS
     Party
    0.94
    paces
    0.85
     strongh
    0.82
    pace
    0.79
     nominate
    0.77
     stronghold
    0.76
     caucus
    0.75
     Caucus
    0.72
    hift
    0.71
    Democrats
    0.71
    Activations Density 0.040%

    No Known Activations