© 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. 7-RES-JB
    11. 13493
    Prev
    Next
    INDEX
    Explanations

    the word "Wood" followed by numbers corresponding to place names or titles

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of the name "Wood."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ional
    -0.77
     disenfranch
    -0.74
     aver
    -0.72
    uates
    -0.69
    uated
    -0.69
    âĸ¬âĸ¬
    -0.67
     delinqu
    -0.66
    BILITY
    -0.65
     extortion
    -0.62
    uate
    -0.62
    POSITIVE LOGITS
    ruff
    1.36
    bridge
    1.19
    stock
    1.12
    lands
    1.11
    lake
    1.11
    leigh
    1.10
    working
    1.08
    cutting
    1.03
    burn
    1.03
    riter
    1.01
    Activations Density 0.019%

    No Known Activations