© 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. 17829
    Prev
    Next
    INDEX
    Explanations

    references to sticks or stick-like objects

    oai_token-act-pair · gpt-3.5-turbo

    references to sticks, including various types and uses of sticks

    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
     unfocusedRange
    -0.85
    ONT
    -0.67
    actionDate
    -0.67
    gdala
    -0.66
    âĸ¬
    -0.63
    æĹ
    -0.63
    APH
    -0.63
     Anthem
    -0.62
     Cannes
    -0.62
    ndum
    -0.62
    POSITIVE LOGITS
    holder
    1.00
    iness
    0.97
    pole
    0.97
    handle
    0.92
    holders
    0.92
    handled
    0.90
    river
    0.89
    tip
    0.88
     blender
    0.87
    lers
    0.86
    Activations Density 0.023%

    No Known Activations