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. 7-RES-JB
    6. 23161
    Prev
    Next
    INDEX
    Explanations

    instances of physical impact or injury

    oai_token-act-pair · gpt-3.5-turbo

    references to physical impact or injury

    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
    outh
    -0.63
     goodwill
    -0.61
    ensical
    -0.61
    ylum
    -0.60
     organising
    -0.60
     Psychiatry
    -0.60
     splend
    -0.60
     colours
    -0.58
     positives
    -0.58
    inqu
    -0.58
    POSITIVE LOGITS
    ched
    1.18
    ches
    0.82
     dodged
    0.82
    boxes
    0.81
     squarely
    0.80
    eor
    0.78
    box
    0.75
    lasses
    0.75
    rators
    0.74
    ãĤ°
    0.71
    Activations Density 0.054%

    No Known Activations