© 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. 10-RES-JB
    11. 2706
    Prev
    Next
    INDEX
    Explanations

    times when an action or event is initiated or completed

    oai_token-act-pair · gpt-3.5-turbo

    the word "Once."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rug
    -0.83
     Cosponsors
    -0.81
    orts
    -0.74
    æ©
    -0.70
    Õ
    -0.69
    ================================================================
    -0.68
    orting
    -0.68
    ãĤ®
    -0.67
    WAYS
    -0.65
    mers
    -0.65
    POSITIVE LOGITS
     again
    1.35
     Upon
    0.98
     upon
    0.98
     bitten
    0.90
     mastered
    0.88
     satisfied
    0.87
     completed
    0.84
     seated
    0.83
     Again
    0.83
     reunited
    0.79
    Activations Density 0.027%

    No Known Activations