© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 10178
    Prev
    Next
    INDEX
    Explanations

    words related to wood

    oai_token-act-pair · gpt-3.5-turbo

    references to wood and its various uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orsche
    -0.73
     Sunshine
    -0.69
    rences
    -0.68
    Reason
    -0.68
     Hunger
    -0.68
     Romeo
    -0.67
     Hogan
    -0.67
     Goodbye
    -0.67
    ochet
    -0.66
     Kis
    -0.65
    POSITIVE LOGITS
    grain
    1.17
    working
    1.14
     pulp
    1.10
    wind
    1.06
    worker
    1.04
     dow
    0.98
    workers
    0.98
    cuts
    0.97
    stocks
    0.97
     lumber
    0.96
    Activations Density 0.035%

    No Known Activations