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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 23254
    Prev
    Next
    INDEX
    Explanations

    references to superhero movies, particularly those related to the Justice League and Wonder Woman

    oai_token-act-pair · gpt-3.5-turbo

    references to superhero characters and their associated movies within the DC universe

    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
    hower
    -0.84
    ateur
    -0.83
    grain
    -0.74
    mediate
    -0.74
    sweet
    -0.73
    mination
    -0.72
    embed
    -0.72
    uning
    -0.71
    unicip
    -0.70
    housing
    -0.68
    POSITIVE LOGITS
    buster
    1.05
     Kenobi
    0.97
     Comics
    0.96
     villains
    0.96
     Characters
    0.93
     Superman
    0.91
     Batman
    0.91
    Batman
    0.89
     villain
    0.88
     Costume
    0.88
    Activations Density 0.159%

    No Known Activations