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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 15073
    Prev
    Next
    INDEX
    Explanations

    mentions of peanuts or peanut-related products

    oai_token-act-pair · gpt-3.5-turbo

    references to peanuts and peanut-based products

    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
    station
    -0.77
    Vers
    -0.77
     Vend
    -0.77
     Zur
    -0.70
     Recover
    -0.69
     Mour
    -0.68
     VOL
    -0.67
    Ver
    -0.67
    uploads
    -0.67
    Station
    -0.67
    POSITIVE LOGITS
     peanut
    3.70
     peanuts
    2.42
    anut
    2.12
     peas
    1.28
     almond
    1.26
     tofu
    1.25
     almonds
    1.22
     peach
    1.20
     cocoa
    1.18
     soy
    1.18
    Activations Density 0.032%

    No Known Activations