© 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. 7-RES-JB
    11. 23716
    Prev
    Next
    INDEX
    Explanations

    negative events or challenges

    oai_token-act-pair · gpt-3.5-turbo

    negations or negative implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Heads
    -0.69
    STER
    -0.68
     Confederation
    -0.67
    lishing
    -0.66
     Vessel
    -0.63
    )=(
    -0.62
     Shades
    -0.61
     Ell
    -0.60
    APTER
    -0.59
     DOI
    -0.59
    POSITIVE LOGITS
    be
    0.81
    ali
    0.78
    gage
    0.78
    you
    0.78
    call
    0.78
    dep
    0.77
    crime
    0.76
    ev
    0.75
    say
    0.75
    farm
    0.75
    Activations Density 0.038%

    No Known Activations