© 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. 8-RES-JB
    11. 20395
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal hearings or investigations

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation or structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tended
    -0.76
    vation
    -0.72
     pooled
    -0.72
     underestimated
    -0.70
     empowerment
    -0.69
     kindness
    -0.67
    riage
    -0.67
     realised
    -0.66
     systematically
    -0.66
     everywhere
    -0.66
    POSITIVE LOGITS
     Meanwhile
    1.28
     Sources
    1.17
     Currently
    1.15
     Presumably
    1.14
     According
    1.11
     Hopefully
    1.09
     Regardless
    1.08
     Officials
    1.05
     Additionally
    1.04
     However
    1.03
    Activations Density 0.466%

    No Known Activations