© 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 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. 9-RES-JB
    11. 1978
    Prev
    Next
    INDEX
    Explanations

    instructions or steps related to food preparation

    oai_token-act-pair · gpt-3.5-turbo

    instructions related to cooking or food preparation techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ublic
    -0.85
    ategories
    -0.85
    eworld
    -0.77
    ylum
    -0.74
    encia
    -0.73
    ghazi
    -0.70
    CLUS
    -0.68
     greets
    -0.67
     transcripts
    -0.66
    cci
    -0.64
    POSITIVE LOGITS
     scissors
    1.25
     fingert
    1.14
     pencil
    1.09
     fingers
    1.07
     blender
    1.04
     brush
    1.02
     finger
    1.01
     fingertips
    1.00
     teaspoon
    0.99
     tong
    0.98
    Activations Density 0.256%

    No Known Activations