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. 0-RES-JB
    6. 4538
    Prev
    Next
    INDEX
    Explanations

    references to online shops or physical stores, particularly within the context of the hip-hop culture

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "hop" in various contexts related to hip-hop culture or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mechdragon
    -0.73
     definition
    -0.66
    ined
    -0.65
     Sed
    -0.63
     Silver
    -0.63
     certs
    -0.61
     Sovereign
    -0.61
     definitions
    -0.60
     dense
    -0.60
     Void
    -0.59
    POSITIVE LOGITS
    hop
    4.89
    hops
    3.39
    Hop
    2.23
     Hop
    1.69
     hop
    1.56
    ho
    1.42
    haw
    1.33
    hirt
    1.29
    soon
    1.21
    hip
    1.20
    Activations Density 0.008%

    No Known Activations