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. 5382
    Prev
    Next
    INDEX
    Explanations

    words related to smoothness or smooth textures

    oai_token-act-pair · gpt-3.5-turbo

    references to smoothness or smooth actions

    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
    arium
    -0.72
    ENTS
    -0.69
    EMP
    -0.67
    REL
    -0.66
    ilogy
    -0.66
     Ancients
    -0.64
    CVE
    -0.64
    IGHTS
    -0.63
    acons
    -0.63
    ENT
    -0.62
    POSITIVE LOGITS
     sailing
    1.07
    ies
    0.98
     smooth
    0.94
    ness
    0.91
     transitions
    0.91
    ie
    0.89
     Smooth
    0.79
     transition
    0.79
    sheet
    0.78
    hattan
    0.77
    Activations Density 0.020%

    No Known Activations