© 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. 0-RES-JB
    11. 1133
    Prev
    Next
    INDEX
    Explanations

    keywords related to the system of psychiatric assessment known as the Axis system

    oai_token-act-pair · gpt-3.5-turbo

    references to specific "Axis" categories and the "Anthem" entity in a health-related context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cook
    -0.87
     stove
    -0.79
     Cook
    -0.79
     Cooking
    -0.73
     Kenny
    -0.71
    owan
    -0.70
     Ol
    -0.70
     Bok
    -0.70
    Ol
    -0.70
    wyn
    -0.67
    POSITIVE LOGITS
     Anthem
    1.85
     Axis
    1.73
     MGM
    1.61
     fascism
    1.56
     AMA
    1.42
     Fasc
    1.39
     fascist
    1.37
     fascists
    1.30
    fascist
    1.30
     Cadillac
    1.25
    Activations Density 0.060%

    No Known Activations