© 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. 11-RES-JB
    11. 9833
    Prev
    Next
    INDEX
    Explanations

    error messages prompting the user to retry an action

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating errors or prompts for user action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.56
    ants
    -0.56
    wik
    -0.55
    ortium
    -0.55
    kept
    -0.53
    è¦
    -0.52
     carcin
    -0.52
    DEF
    -0.51
    shown
    -0.51
    senal
    -0.51
    POSITIVE LOGITS
     Oops
    0.75
     repaired
    0.67
     Try
    0.63
     try
    0.59
    Try
    0.58
     Fixes
    0.57
     Refresh
    0.57
     Clintons
    0.56
     reload
    0.55
     Runtime
    0.55
    Activations Density 0.025%

    No Known Activations