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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 11801
    Prev
    Next
    INDEX
    Explanations

    references to folk-related content

    oai_token-act-pair · gpt-3.5-turbo

    references to folk music or folk culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xus
    -0.77
    Effective
    -0.71
    lain
    -0.68
    xual
    -0.63
     Rack
    -0.60
    isites
    -0.60
     barrel
    -0.59
     Effective
    -0.59
     Higgins
    -0.59
     funnel
    -0.59
    POSITIVE LOGITS
    lore
    1.31
    lor
    1.17
    tale
    1.15
    folk
    1.15
    endor
    0.92
     tales
    0.92
    estone
    0.91
    worker
    0.91
    mere
    0.90
     tale
    0.82
    Activations Density 0.022%

    No Known Activations