© 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. 3-RES-JB
    11. 15693
    Prev
    Next
    INDEX
    Explanations

    words related to physical activities and competitions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to physical activities and injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yss
    -0.65
    ANC
    -0.60
    Commission
    -0.58
    ANA
    -0.55
     Gulf
    -0.55
    Franc
    -0.55
     Sweeney
    -0.53
    BUG
    -0.53
     reconstruction
    -0.53
    Harris
    -0.52
    POSITIVE LOGITS
    paces
    1.39
    mith
    1.32
    hips
    1.32
    creen
    1.30
    heet
    1.29
    ettings
    1.26
    pring
    1.26
    uggest
    1.25
    pace
    1.24
    hip
    1.23
    Activations Density 0.314%

    No Known Activations