© 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. 1908
    Prev
    Next
    INDEX
    Explanations

    quantitative information about frequency or quantity related to various topics

    oai_token-act-pair · gpt-3.5-turbo

    quantitative phrases related to occurrences and frequencies

    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
    XT
    -0.64
    hess
    -0.63
     Clarks
    -0.62
    ORY
    -0.62
     Journals
    -0.61
    bley
    -0.59
     Parties
    -0.58
     srfAttach
    -0.57
     benches
    -0.56
     lightly
    -0.56
    POSITIVE LOGITS
     year
    1.36
     month
    1.11
    year
    1.11
     decade
    1.00
     week
    0.99
     day
    0.97
    month
    0.96
     weekday
    0.91
     calendar
    0.91
    years
    0.89
    Activations Density 0.082%

    No Known Activations