© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13610
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Pol" with a high level of activation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of police and law enforcement terms

    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
    DOM
    -0.82
     mileage
    -0.77
    estate
    -0.71
     tf
    -0.70
    attribute
    -0.69
     descriptor
    -0.69
    erences
    -0.68
     attribute
    -0.67
    agar
    -0.65
    huge
    -0.65
    POSITIVE LOGITS
     Pol
    3.96
    Pol
    2.60
     pol
    2.00
    pol
    1.85
     POL
    1.77
     Polo
    1.51
    POL
    1.49
     Poles
    1.34
     Polish
    1.32
     polio
    1.17
    Activations Density 0.027%

    No Known Activations