© 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. 11-RES-JB
    11. 18550
    Prev
    Next
    INDEX
    Explanations

    terms related to financial charges or costs

    oai_token-act-pair · gpt-3.5-turbo

    references to fees and charges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ################
    -0.69
    ulnerable
    -0.68
    ational
    -0.68
    lihood
    -0.67
    DonaldTrump
    -0.65
    ullivan
    -0.64
     tense
    -0.64
     Alma
    -0.63
    ogue
    -0.62
    ometown
    -0.61
    POSITIVE LOGITS
     levied
    1.24
     waived
    1.14
     waivers
    1.08
     charged
    1.04
     waiver
    1.01
    payer
    0.98
    payers
    0.95
     payable
    0.94
    umed
    0.93
     imposed
    0.93
    Activations Density 0.046%

    No Known Activations