© 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. 7-RES-JB
    11. 21689
    Prev
    Next
    INDEX
    Explanations

    words related to physical fighting or aggressive actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "punch" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uve
    -0.86
    abeth
    -0.84
    aird
    -0.69
    rians
    -0.67
    abor
    -0.66
    udic
    -0.65
    icter
    -0.64
    heimer
    -0.64
    uph
    -0.63
    OTE
    -0.63
    POSITIVE LOGITS
    bowl
    1.24
     punches
    0.85
     punch
    0.85
     holes
    0.83
    ting
    0.78
    bag
    0.76
    outs
    0.75
     punching
    0.74
     Punch
    0.73
    apult
    0.73
    Activations Density 0.025%

    No Known Activations