© 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. 17182
    Prev
    Next
    INDEX
    Explanations

    political terms related to control and power

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political party dynamics and electoral control

    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
     voy
    -0.86
    obar
    -0.77
     solitude
    -0.69
     dolphins
    -0.69
     visitation
    -0.69
     Amen
    -0.65
    Atl
    -0.65
     liner
    -0.64
     Perse
    -0.63
     Seraph
    -0.62
    POSITIVE LOGITS
     majorities
    1.18
     caucus
    1.16
     Caucus
    1.02
     nominate
    1.02
    Republicans
    1.02
     electoral
    0.98
    isans
    0.98
     repeal
    0.97
    Democrats
    0.97
     centr
    0.96
    Activations Density 0.564%

    No Known Activations