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. 9-RES-JB
    6. 14935
    Prev
    Next
    INDEX
    Explanations

    descriptions of visual appearance or aesthetics

    oai_token-act-pair · gpt-3.5-turbo

    evaluative descriptors related to visual appearance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    trl
    -0.67
    limit
    -0.65
    learning
    -0.65
     Osw
    -0.64
    ference
    -0.64
     Candle
    -0.63
    mental
    -0.62
    vention
    -0.62
    ulla
    -0.62
    ricular
    -0.61
    POSITIVE LOGITS
     like
    0.95
     strikingly
    0.89
     awfully
    0.88
     prett
    0.86
     innocuous
    0.85
     identical
    0.85
     sleek
    0.83
     vaguely
    0.83
     suspic
    0.82
     blurry
    0.79
    Activations Density 0.065%

    No Known Activations