© 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. 4675
    Prev
    Next
    INDEX
    Explanations

    references to quantities or amounts of people or things

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "number" and its related contextual usage

    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
    dit
    -0.73
    INTON
    -0.66
     fixme
    -0.63
    din
    -0.62
    ALD
    -0.62
    arna
    -0.61
    lace
    -0.61
    hem
    -0.60
    imon
    -0.60
     Honour
    -0.59
    POSITIVE LOGITS
     of
    0.82
     number
    0.80
    number
    0.73
     expended
    0.71
     quoted
    0.71
     involved
    0.69
     recorded
    0.69
     allowable
    0.69
     plummeted
    0.65
     varies
    0.65
    Activations Density 0.078%

    No Known Activations