© 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. 10-RES-JB
    11. 4708
    Prev
    Next
    INDEX
    Explanations

    actions or suggestions related to policy-making and governance

    oai_token-act-pair · gpt-3.5-turbo

    sentences emphasizing governmental or institutional accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     happening
    -0.73
     lurking
    -0.68
     dying
    -0.68
     trailing
    -0.66
     stumbling
    -0.66
     guessing
    -0.64
    awed
    -0.64
     falling
    -0.64
     coloured
    -0.64
     consequential
    -0.63
    POSITIVE LOGITS
     Provide
    1.62
    Create
    1.49
     Reduce
    1.47
     Create
    1.46
    Increase
    1.40
    cknow
    1.38
     Improve
    1.38
     Remove
    1.37
    Apply
    1.36
    Allow
    1.34
    Activations Density 0.265%

    No Known Activations