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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11110
    Prev
    Next
    INDEX
    Explanations

    instances of the word "nut"

    oai_token-act-pair · gpt-3.5-turbo

    references to nuts

    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
     Ward
    -0.70
     cla
    -0.61
     clauses
    -0.60
     debts
    -0.60
     caption
    -0.59
     autonomous
    -0.59
     executions
    -0.58
     Cla
    -0.58
     dispos
    -0.58
     Johnson
    -0.57
    POSITIVE LOGITS
    nut
    4.87
    nuts
    4.06
    Nut
    1.99
     Nut
    1.61
     nut
    1.54
     nuts
    1.24
    hog
    1.02
    nu
    1.01
     almonds
    1.00
    anut
    0.99
    Activations Density 0.005%

    No Known Activations