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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 10654
    Prev
    Next
    INDEX
    Explanations

    references to physical violence or combat

    oai_token-act-pair · gpt-3.5-turbo

    references to physical violence, specifically punching

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ministry
    -0.83
    arma
    -0.76
    recomm
    -0.71
     undert
    -0.71
     Lutheran
    -0.71
     Drift
    -0.70
     Ministry
    -0.68
     Ministers
    -0.67
     Recomm
    -0.66
     Reaper
    -0.64
    POSITIVE LOGITS
     punched
    3.28
     punching
    2.73
     punches
    2.29
     punch
    1.93
     Punch
    1.51
     fists
    1.22
     stabbed
    1.19
     shoved
    1.15
     slapped
    1.14
     sucker
    1.14
    Activations Density 0.025%

    No Known Activations