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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 23573
    Prev
    Next
    INDEX
    Explanations

    phrases related to the name "Woods."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Woods."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itia
    -0.70
    imated
    -0.64
    ī
    -0.64
    orescent
    -0.64
    ITAL
    -0.63
    Hispanic
    -0.63
    inventoryQuantity
    -0.63
    otation
    -0.61
     Yel
    -0.61
    esthetic
    -0.60
    POSITIVE LOGITS
     Woods
    1.12
     Hole
    0.99
    lake
    0.90
    hog
    0.84
    heimer
    0.84
    hole
    0.84
    mallow
    0.84
    bury
    0.83
    hed
    0.82
     Creek
    0.81
    Activations Density 0.007%

    No Known Activations