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

    Neuronpedia

    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. 7-RES-JB
    11. 2919
    Prev
    Next
    INDEX
    Explanations

    instructions or steps related to cooking a variety of dishes

    oai_token-act-pair · gpt-3.5-turbo

    instructions related to cooking processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ById
    -0.76
     vest
    -0.71
    ticket
    -0.70
     Cele
    -0.68
    å¦
    -0.66
     priceless
    -0.66
    女
    -0.66
     emph
    -0.65
    desc
    -0.65
     tickets
    -0.65
    POSITIVE LOGITS
     pH
    1.24
     boiling
    1.18
     cooled
    1.17
     chilled
    1.16
     fermentation
    1.13
     soak
    1.12
     soaked
    1.08
     yeast
    1.07
     temperature
    1.06
     baking
    1.05
    Activations Density 0.411%

    No Known Activations