© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12201
    Prev
    Next
    INDEX
    Explanations

    mentions of the start or end of someone's term in an official position

    oai_token-act-pair · gpt-3.5-turbo

    references to taking office and the concept of political leadership transitions

    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
    alog
    -0.79
    ostic
    -0.74
    Unity
    -0.67
    ologist
    -0.66
    alore
    -0.66
    isoft
    -0.66
    MQ
    -0.65
    Ku
    -0.63
     Sharp
    -0.61
    ologists
    -0.61
    POSITIVE LOGITS
     pledging
    0.95
    clinton
    0.84
    holders
    0.76
    long
    0.72
     swearing
    0.72
    velt
    0.71
     hopeful
    0.70
     concurrently
    0.68
     pledges
    0.68
    manship
    0.68
    Activations Density 0.048%

    No Known Activations