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. 6-RES-JB
    6. 10216
    Prev
    Next
    INDEX
    Explanations

    words related to surface finishing and polishing

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to finishes and textures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zee
    -0.75
     Stras
    -0.74
    Connell
    -0.69
     Somers
    -0.68
    Wiki
    -0.65
    itar
    -0.65
    \\\\\\\\
    -0.65
    sic
    -0.65
    OTAL
    -0.65
    edia
    -0.64
    POSITIVE LOGITS
     coating
    1.08
     coat
    0.98
     paint
    0.94
     color
    0.93
     polish
    0.92
     texture
    0.90
     tint
    0.90
     stripe
    0.88
     dye
    0.86
     gloss
    0.84
    Activations Density 0.147%

    No Known Activations