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. 3-RES-JB
    6. 7814
    Prev
    Next
    INDEX
    Explanations

    mentions of graffiti and related contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "graffiti."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    othal
    -0.95
    obar
    -0.87
    ouple
    -0.85
    inda
    -0.81
    rox
    -0.80
    ruciating
    -0.73
     McDonnell
    -0.73
    itsch
    -0.72
    ŃĶ
    -0.72
    othy
    -0.72
    POSITIVE LOGITS
     graffiti
    1.03
    ffiti
    0.78
     mural
    0.73
     littered
    0.73
    writing
    0.70
    punk
    0.69
    writers
    0.69
     legend
    0.69
     artists
    0.69
     tagging
    0.68
    Activations Density 0.013%

    No Known Activations