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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 14739
    Prev
    Next
    INDEX
    Explanations

    quantities or statistics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "of the" along with numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cation
    -0.80
    growth
    -0.71
    lly
    -0.69
    veland
    -0.68
    selves
    -0.65
    orc
    -0.64
     misunder
    -0.62
    arity
    -0.62
    theless
    -0.62
    cedes
    -0.62
    POSITIVE LOGITS
     surveyed
    0.97
     thirteen
    0.92
     seven
    0.87
     eleven
    0.86
     nine
    0.86
     sixteen
    0.85
     fourteen
    0.84
     eight
    0.83
     five
    0.80
     four
    0.80
    Activations Density 0.057%

    No Known Activations