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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22751
    Prev
    Next
    INDEX
    Explanations

    numeric information related to amounts of money or quantities

    oai_token-act-pair · gpt-3.5-turbo

    numeric values associated with financial or quantitative data

    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
    tnc
    -0.70
    natureconservancy
    -0.68
    uncture
    -0.63
    ãĥ¤
    -0.63
    issue
    -0.63
    idable
    -0.57
    leader
    -0.57
     amplified
    -0.56
    Leader
    -0.54
     precedence
    -0.54
    POSITIVE LOGITS
     apiece
    0.90
     consecut
    0.89
     during
    0.88
     concurrently
    0.81
     ago
    0.80
     throughout
    0.78
     before
    0.75
     domestically
    0.72
     (£
    0.72
     annually
    0.69
    Activations Density 0.352%

    No Known Activations