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. 0-RES-JB
    6. 6122
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the word "wood."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "wood" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     masc
    -0.72
     dem
    -0.71
     flu
    -0.69
     simultaneous
    -0.65
     UID
    -0.62
     unamb
    -0.62
     mega
    -0.60
     timely
    -0.60
     indef
    -0.60
     messaging
    -0.59
    POSITIVE LOGITS
    wood
    4.35
    WOOD
    2.66
    woods
    2.65
    Wood
    1.74
     wood
    1.45
    hurst
    1.29
     Wood
    1.27
    brook
    1.26
    wine
    1.21
    stone
    1.20
    Activations Density 0.015%

    No Known Activations