© 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. 16744
    Prev
    Next
    INDEX
    Explanations

    names of political figures and leaders, particularly associated with regions in conflict or turmoil

    oai_token-act-pair · gpt-3.5-turbo

    references to political leaders or dictators

    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
    rawdownloadcloneembedreportprint
    -0.66
     anecd
    -0.60
     rhy
    -0.54
     pestic
    -0.49
    staking
    -0.48
     pamph
    -0.47
     nep
    -0.47
     acron
    -0.47
    eele
    -0.46
     pse
    -0.46
    POSITIVE LOGITS
    ·
    0.56
     ÂŃ
    0.55
    Ħ¢
    0.52
    ª
    0.51
    á
    0.51
    «
    0.49
    lad
    0.47
    ®
    0.47
    °
    0.47
    ĩ
    0.46
    Activations Density 0.884%

    No Known Activations