© 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. 23042
    Prev
    Next
    INDEX
    Explanations

    symbols or formatting inconsistencies

    oai_token-act-pair · gpt-3.5-turbo

    large quantities or measures of experienced consequences

    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
    odynam
    -0.64
    ensibly
    -0.62
    utical
    -0.60
    aturdays
    -0.60
    hetti
    -0.58
    hement
    -0.58
     estranged
    -0.58
    abwe
    -0.57
    ogly
    -0.57
    icas
    -0.56
    POSITIVE LOGITS
    ³³³
    1.14
    ³³³³³³³³
    1.11
    ³³³³
    1.11
    ³³³³³³³³³³³³³³³³
    1.01
    ³³
    0.88
     largeDownload
    0.84
    CVE
    0.80
    Anonymous
    0.78
    Anyway
    0.78
    rawdownloadcloneembedreportprint
    0.78
    Activations Density 0.559%

    No Known Activations