Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 22448
    Prev
    Next
    INDEX
    Explanations

    words related to physical violence or forceful action

    oai_token-act-pair · gpt-3.5-turbo

    words related to physical impact or aggression, specifically variations of the term "punch."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uve
    -0.94
    abeth
    -0.81
    mberg
    -0.69
    udic
    -0.67
    stellar
    -0.66
    ignty
    -0.66
    rians
    -0.65
    Private
    -0.64
     Citizen
    -0.64
    uph
    -0.64
    POSITIVE LOGITS
    bowl
    1.23
     punch
    0.88
     punches
    0.86
     holes
    0.81
    aneers
    0.78
    sticks
    0.78
    outs
    0.74
     elbows
    0.74
     bowl
    0.73
     Punch
    0.73
    Activations Density 0.020%

    No Known Activations