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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 8-RES-JB
    6. 3618
    Prev
    Next
    INDEX
    Explanations

    names or references to the musician Avicii

    oai_token-act-pair · gpt-3.5-turbo

    variations of the name "Avicii" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewed
    -0.66
     gears
    -0.66
    mot
    -0.66
     commissions
    -0.65
    essional
    -0.65
    hern
    -0.63
    enhagen
    -0.61
     corners
    -0.61
    espie
    -0.61
    telling
    -0.59
    POSITIVE LOGITS
    atis
    0.74
    «ĺ
    0.74
    çIJ
    0.73
    ILE
    0.70
    ģĸ
    0.68
    gard
    0.65
    CRIP
    0.65
    EVA
    0.64
    »Ĵ
    0.64
    ª
    0.64
    Activations Density 0.077%

    No Known Activations