© 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. 0-RES-JB
    11. 9905
    Prev
    Next
    INDEX
    Explanations

    references to the "Go" programming language

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Go."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     artic
    -0.75
     uneven
    -0.71
     cracks
    -0.68
     lat
    -0.64
     invol
    -0.62
     profession
    -0.62
     temperature
    -0.62
     professions
    -0.62
     moderate
    -0.60
     cracked
    -0.60
    POSITIVE LOGITS
    Go
    3.69
     Go
    2.14
    GO
    2.09
    go
    2.04
     GO
    1.45
    Going
    1.24
    Skip
    1.21
     go
    1.18
    Get
    1.17
    Goal
    1.14
    Activations Density 0.014%

    No Known Activations