© 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. 9468
    Prev
    Next
    INDEX
    Explanations

    terms related to political processes and decision-making such as referendums and votes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'b' in various contexts

    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
    chwitz
    -0.69
     Rack
    -0.61
    CLA
    -0.60
    letters
    -0.60
     Piper
    -0.60
     Guerrero
    -0.59
     Nord
    -0.57
    Legendary
    -0.57
     Otto
    -0.56
     eminent
    -0.56
    POSITIVE LOGITS
    isc
    0.89
    ophile
    0.88
    ophobia
    0.87
    ophobic
    0.86
    udging
    0.84
    idation
    0.81
    etime
    0.81
    oshenko
    0.80
    ifix
    0.78
    odynamics
    0.78
    Activations Density 0.071%

    No Known Activations