© 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. 11-RES-JB
    11. 22694
    Prev
    Next
    INDEX
    Explanations

    words related to various actions or concepts in discussions or debates

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with controversy and political maneuvers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     *.
    -0.72
     Conduct
    -0.62
     Supported
    -0.61
     Medline
    -0.61
     Due
    -0.60
    ":["
    -0.60
     Sind
    -0.60
    .''.
    -0.60
     consecut
    -0.59
     Prior
    -0.59
    POSITIVE LOGITS
    ocracy
    1.10
    ocratic
    1.05
    iest
    1.03
    ariat
    0.89
    horse
    0.88
    leader
    0.86
    less
    0.84
    ometer
    0.82
    book
    0.81
    packed
    0.81
    Activations Density 0.545%

    No Known Activations