© 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. 8-RES-JB
    11. 2445
    Prev
    Next
    INDEX
    Explanations

    words related to logs or record-keeping

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts related to logs, particularly in a technical or computing context

    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
    terday
    -0.92
    xual
    -0.69
    HAEL
    -0.63
    riages
    -0.61
     Albion
    -0.57
     Markets
    -0.56
     Rav
    -0.55
     Debor
    -0.55
     Arabian
    -0.55
     preschool
    -0.54
    POSITIVE LOGITS
    gers
    1.38
    istically
    1.28
    istics
    1.26
    ging
    1.22
    istical
    1.20
    itech
    1.10
    ged
    1.08
    istic
    1.04
    otype
    1.00
    ger
    0.99
    Activations Density 0.044%

    No Known Activations