© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 1888
    Prev
    Next
    INDEX
    Explanations

    political entities and figures, as well as places and regions related to politics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to official governmental actions or statements

    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
     havoc
    -0.63
    chwitz
    -0.57
     wrinkles
    -0.57
     poses
    -0.52
     cloudy
    -0.51
     exposes
    -0.50
     pir
    -0.50
     Gleaming
    -0.50
     Yankee
    -0.49
     fires
    -0.49
    POSITIVE LOGITS
    mbuds
    0.77
     Editors
    0.72
     stakeholders
    0.67
    Council
    0.67
    ij士
    0.66
     consortium
    0.64
     representatives
    0.64
    ographers
    0.63
     editors
    0.62
    ãĤ¢ãĥ«
    0.62
    Activations Density 0.873%

    No Known Activations