© 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. 6-RES-JB
    11. 4245
    Prev
    Next
    INDEX
    Explanations

    topics related to various governmental and political issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to law, crime, and governmental topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mahjong
    -0.76
     Seal
    -0.75
    lyak
    -0.75
     Versus
    -0.72
     Flesh
    -0.72
     Knot
    -0.70
     Hog
    -0.69
     Innocent
    -0.69
     Smooth
    -0.69
     Furious
    -0.69
    POSITIVE LOGITS
    "}],"
    0.78
    archives
    0.75
     warr
    0.72
    complex
    0.72
    ãģ®ç
    0.71
     condem
    0.71
     encount
    0.70
     tradem
    0.70
    mares
    0.69
    oenix
    0.68
    Activations Density 0.042%

    No Known Activations