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. 1-RES-JB
    6. 1330
    Prev
    Next
    INDEX
    Explanations

    mentions of the Marvel character "Hulk."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the character "Hulk" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    creen
    -1.05
    colo
    -0.90
    bryce
    -0.82
     chords
    -0.82
    nette
    -0.81
    ABLE
    -0.80
    ãĤ¤ãĥĪ
    -0.80
    ynthesis
    -0.79
    cence
    -0.79
    olson
    -0.77
    POSITIVE LOGITS
     Trophy
    0.80
    valued
    0.71
     gau
    0.71
     Marshal
    0.71
     Sport
    0.70
     Io
    0.70
     Sah
    0.66
     Soccer
    0.66
     Zero
    0.65
     Regener
    0.65
    Activations Density 0.028%

    No Known Activations