© 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. 9-RES-JB
    11. 3652
    Prev
    Next
    INDEX
    Explanations

    negative or controversial terms related to politics, media, and ideology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political and social controversy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ecycle
    -0.75
    etus
    -0.73
    rower
    -0.67
    athi
    -0.64
    insula
    -0.63
    otaur
    -0.63
    ructure
    -0.62
    mentioned
    -0.62
    ocamp
    -0.61
     reins
    -0.61
    POSITIVE LOGITS
     fodder
    1.29
     shorthand
    0.98
    speak
    0.93
     territory
    0.92
     filler
    0.80
     incarn
    0.79
     heaven
    0.78
     anyway
    0.77
    evidence
    0.75
     unto
    0.75
    Activations Density 0.416%

    No Known Activations