© 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. 4-RES-JB
    11. 10273
    Prev
    Next
    INDEX
    Explanations

    words related to snacks

    oai_token-act-pair · gpt-3.5-turbo

    mentions of snacks and snack-related items

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

    No Comments

    Negative Logits
    ne
    -0.75
     Caldwell
    -0.63
    nec
    -0.62
     plur
    -0.61
     negatives
    -0.61
     transcription
    -0.60
     wills
    -0.60
     Aux
    -0.60
     Wein
    -0.60
     secession
    -0.59
    POSITIVE LOGITS
     cereal
    1.02
     snacks
    0.98
     tray
    0.92
     snack
    0.90
     tasty
    0.90
     meal
    0.89
     beverage
    0.87
     eaten
    0.86
     cookies
    0.86
     dessert
    0.85
    Activations Density 0.032%

    No Known Activations