© 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. 15285
    Prev
    Next
    INDEX
    Explanations

    references to superlatives or extremes in size, status, or importance

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "the world" or superlative comparisons related to global significance

    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
    imon
    -0.84
    icer
    -0.83
    lav
    -0.77
    regon
    -0.74
    hift
    -0.72
    okane
    -0.72
    odox
    -0.72
    zin
    -0.71
    escription
    -0.70
    irs
    -0.70
    POSITIVE LOGITS
     besides
    0.69
     imaginable
    0.67
     nowadays
    0.66
    .'
    0.66
    ,'"
    0.64
     Jew
    0.64
     (~
    0.63
     today
    0.63
    !'
    0.62
     ever
    0.62
    Activations Density 0.077%

    No Known Activations