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

    Neuronpedia

    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. 11-RES-JB
    11. 23038
    Prev
    Next
    INDEX
    Explanations

    politically themed words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    remarks or comments made during public forums or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    *)
    -0.90
    £
    -0.79
    ???
    -0.74
    ????
    -0.73
    shit
    -0.73
    ?????
    -0.72
    ovember
    -0.71
    ?!
    -0.70
    )?
    -0.69
    Advertisements
    -0.69
    POSITIVE LOGITS
     flanked
    0.97
     amid
    0.91
     midday
    0.77
     unveiling
    0.77
     alongside
    0.71
     outlining
    0.70
     onstage
    0.70
     ahead
    0.69
     undersc
    0.69
     capped
    0.68
    Activations Density 0.464%

    No Known Activations