© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 11404
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and leaders

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political leaders and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     testament
    -0.60
     ·
    -0.59
     survives
    -0.58
     juggling
    -0.57
     tended
    -0.57
     sucks
    -0.56
     paradox
    -0.55
     credits
    -0.55
     tends
    -0.55
     derives
    -0.55
    POSITIVE LOGITS
    omever
    0.80
     Mayor
    0.68
     President
    0.67
    venge
    0.63
     counterpart
    0.59
     Task
    0.59
    SPONSORED
    0.59
     presumptive
    0.58
     Gov
    0.58
     counterparts
    0.58
    Activations Density 0.449%

    No Known Activations