© 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. 10-RES-JB
    11. 12374
    Prev
    Next
    INDEX
    Explanations

    steps or instructions for a cooking recipe

    oai_token-act-pair · gpt-3.5-turbo

    references to cooking and food preparation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ITNESS
    -0.75
     Potential
    -0.67
    âĹ¼
    -0.67
     Offense
    -0.61
     Gamble
    -0.61
     Reasons
    -0.60
     Wanted
    -0.60
    soDeliveryDate
    -0.59
    Pand
    -0.58
     Maps
    -0.58
    POSITIVE LOGITS
     onto
    1.24
     gently
    1.23
     into
    1.15
     downwards
    1.12
     upside
    1.09
     horizontally
    1.06
     upright
    1.05
     halves
    1.04
     downward
    1.04
     overboard
    1.03
    Activations Density 0.165%

    No Known Activations