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. 16505
    Prev
    Next
    INDEX
    Explanations

    references to a specific brand or platform called "Crunchyroll."

    oai_token-act-pair · gpt-3.5-turbo

    references to "Crunch" or closely related terms in the context of tech and media

    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
     emb
    -0.76
     mileage
    -0.69
    ounter
    -0.67
     recreational
    -0.66
    oper
    -0.64
     gull
    -0.63
     Kham
    -0.61
    esthetic
    -0.61
     corps
    -0.60
     Jade
    -0.59
    POSITIVE LOGITS
    Crunch
    1.34
     Crunch
    1.16
    imation
    0.81
    ģĸ
    0.81
    aneers
    0.81
    aido
    0.78
    anos
    0.78
     Rating
    0.77
    rates
    0.77
    Å«
    0.76
    Activations Density 0.021%

    No Known Activations