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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 17291
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical appearance, such as clothing, hair color, and accessories

    oai_token-act-pair · gpt-3.5-turbo

    details about physical appearances and clothing

    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
    mone
    -0.65
    effects
    -0.64
    senal
    -0.63
    iov
    -0.60
    rian
    -0.58
    sense
    -0.58
    cture
    -0.57
    uld
    -0.55
    pol
    -0.54
     exhib
    -0.54
    POSITIVE LOGITS
     Gujar
    0.73
     CLR
    0.68
     and
    0.66
     supplemented
    0.65
    ,,
    0.64
     belonging
    0.63
     consisting
    0.62
    ,,,,
    0.62
     flanked
    0.62
     laced
    0.59
    Activations Density 0.737%

    No Known Activations