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. 8-RES-JB
    6. 12705
    Prev
    Next
    INDEX
    Explanations

    adjectives that describe the visual appearance of things

    oai_token-act-pair · gpt-3.5-turbo

    references to visual appearance or design

    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
    wealth
    -0.67
    cffff
    -0.67
    orb
    -0.66
    stem
    -0.64
    ciating
    -0.64
    ricular
    -0.62
     Tosh
    -0.62
    âĹ¼
    -0.60
    ommod
    -0.60
    onto
    -0.60
    POSITIVE LOGITS
    ahead
    0.98
    behind
    0.82
    prints
    0.75
    checks
    0.74
    nings
    0.73
    atters
    0.71
    anka
    0.71
    outs
    0.71
    bones
    0.71
    edo
    0.67
    Activations Density 0.050%

    No Known Activations