© 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. 14099
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to software errors

    oai_token-act-pair · gpt-3.5-turbo

    terms related to error handling in programming

    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
    electric
    -0.78
    jen
    -0.71
     Aires
    -0.69
    sonian
    -0.69
    Electric
    -0.69
     aspirations
    -0.67
    tsky
    -0.66
    paren
    -0.66
     ambitions
    -0.65
    airo
    -0.65
    POSITIVE LOGITS
     message
    0.93
    prone
    0.90
     messages
    0.89
    ously
    0.88
    Message
    0.88
    Msg
    0.87
     prone
    0.81
     Handling
    0.81
    hooting
    0.81
     Detected
    0.81
    Activations Density 0.055%

    No Known Activations