© 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. 10-RES-JB
    11. 4348
    Prev
    Next
    INDEX
    Explanations

    quotations in text

    oai_token-act-pair · gpt-3.5-turbo

    punctuation or dialogue attributes in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jungle
    -0.90
     Boko
    -0.86
     ninja
    -0.78
     villages
    -0.78
     Bangkok
    -0.75
     mosquito
    -0.75
    ¥µ
    -0.74
     totem
    -0.74
    BAT
    -0.73
     village
    -0.72
    POSITIVE LOGITS
     Stein
    1.64
     Schwe
    1.29
    Ste
    1.27
     Ste
    1.23
     Schwar
    1.16
    Sch
    1.14
    stein
    1.14
     Sche
    1.14
     Wein
    1.14
    STE
    1.11
    Activations Density 0.365%

    No Known Activations