© 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. 1974
    Prev
    Next
    INDEX
    Explanations

    code or programming-related terms, particularly involving errors and data structures

    oai_token-act-pair · gpt-3.5-turbo

    underscores that are part of variable names or identifiers in code

    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
     Casey
    -0.81
     JPM
    -0.78
     Eggs
    -0.77
     Pearce
    -0.77
     Leilan
    -0.76
     Cutting
    -0.75
     Manson
    -0.74
     Vide
    -0.74
     Sachs
    -0.73
    quished
    -0.72
    POSITIVE LOGITS
    modules
    1.18
    mode
    1.18
    gradient
    1.17
    chance
    1.16
    enabled
    1.15
    func
    1.15
    index
    1.15
    type
    1.15
    prefix
    1.14
    pressed
    1.14
    Activations Density 0.024%

    No Known Activations