© 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. 16260
    Prev
    Next
    INDEX
    Explanations

    references to political entities or nations

    oai_token-act-pair · gpt-3.5-turbo
    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
    omething
    -0.68
    istant
    -0.66
    imon
    -0.63
     newsletters
    -0.62
    Initialized
    -0.62
    ension
    -0.61
    urations
    -0.61
    ection
    -0.60
    CV
    -0.60
     Browne
    -0.59
    POSITIVE LOGITS
    wide
    1.14
    hood
    0.91
    eous
    0.82
    States
    0.81
    icans
    0.77
     mourn
    0.75
    rats
    0.73
    's
    0.71
    matically
    0.70
    ogram
    0.70
    Activations Density 0.053%

    No Known Activations