© 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. 3832
    Prev
    Next
    INDEX
    Explanations

    words related to formal investigations or requests for information

    oai_token-act-pair · gpt-3.5-turbo

    terms related to inquiries and investigations

    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
     Depend
    -0.70
    perm
    -0.68
     Diesel
    -0.68
     Kinnikuman
    -0.67
    comb
    -0.65
    enburg
    -0.63
     Magicka
    -0.63
    beard
    -0.63
    Aid
    -0.63
    zer
    -0.62
    POSITIVE LOGITS
     probing
    1.03
    iry
    1.00
    naires
    0.98
    isition
    0.97
     inquiry
    0.93
     inquire
    0.93
     inqu
    0.88
     inquiries
    0.86
    isitions
    0.86
    iries
    0.84
    Activations Density 0.050%

    No Known Activations