© 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. 8-RES-JB
    11. 22410
    Prev
    Next
    INDEX
    Explanations

    financial-related information such as costs, expenses, and budgets

    oai_token-act-pair · gpt-3.5-turbo

    inquiries related to cost and pricing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.68
    scrib
    -0.65
    Pear
    -0.65
    aggressive
    -0.64
    iHUD
    -0.62
    Liter
    -0.62
    cit
    -0.60
    tyard
    -0.60
    perial
    -0.59
    scription
    -0.59
    POSITIVE LOGITS
     WHY
    1.32
     HOW
    1.19
     How
    1.12
     how
    1.11
    why
    1.11
     why
    1.09
    how
    1.07
     Explain
    1.05
    How
    0.96
     whether
    0.95
    Activations Density 0.364%

    No Known Activations