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. 22055
    Prev
    Next
    INDEX
    Explanations

    terms related to project management and infrastructure development

    oai_token-act-pair · gpt-3.5-turbo

    references to governmental and regulatory activities related to infrastructure and project development

    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
    CHAT
    -0.74
    stown
    -0.73
     pestic
    -0.71
    yip
    -0.70
    Spl
    -0.65
    CONCLUS
    -0.63
    Balt
    -0.62
    irlf
    -0.62
    ASY
    -0.61
    Ô
    -0.61
    POSITIVE LOGITS
    paces
    1.17
    hips
    1.11
    hops
    1.07
     abroad
    0.98
    hip
    0.95
    pace
    0.93
     such
    0.93
    mith
    0.89
     alike
    0.87
     overseas
    0.86
    Activations Density 0.471%

    No Known Activations