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. 8-RES-JB
    6. 18958
    Prev
    Next
    INDEX
    Explanations

    phrases related to explosive actions or activities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "blow" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ournal
    -0.72
    heid
    -0.70
    ript
    -0.70
    IX
    -0.68
    ç«
    -0.67
    ately
    -0.66
    cer
    -0.65
    DAQ
    -0.62
    aho
    -0.61
    ivan
    -0.61
    POSITIVE LOGITS
    guns
    0.91
    job
    0.89
    pipe
    0.89
     holes
    0.89
    out
    0.86
    outs
    0.85
    jobs
    0.84
    blown
    0.79
     away
    0.77
     whist
    0.77
    Activations Density 0.032%

    No Known Activations