© 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. 9-RES-JB
    11. 4735
    Prev
    Next
    INDEX
    Explanations

    instructions or steps in a recipe

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating cooking durations and instructions

    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
     Accessed
    -0.75
    leased
    -0.71
    selage
    -0.70
    Born
    -0.69
    ttle
    -0.69
    repre
    -0.67
    ãĥ©
    -0.61
    inese
    -0.61
     Subscribe
    -0.61
    bnb
    -0.60
    POSITIVE LOGITS
     optimal
    0.96
    aging
    0.96
     optimum
    0.92
    agers
    0.88
     awhile
    0.84
     further
    0.84
     instance
    0.84
     clarification
    0.81
     maximum
    0.79
     example
    0.78
    Activations Density 0.113%

    No Known Activations