© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-RES-JB
    11. 8939
    Prev
    Next
    INDEX
    Explanations

    language indicating errors or issues

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "error" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    APTER
    -0.85
    apeake
    -0.76
    nai
    -0.76
    amen
    -0.74
    electric
    -0.73
    ±
    -0.72
    idal
    -0.71
    bors
    -0.70
    apy
    -0.70
    bledon
    -0.67
    POSITIVE LOGITS
     error
    0.99
     guiActiveUn
    0.99
    ously
    0.96
     errors
    0.85
     Error
    0.80
     margin
    0.76
     deceive
    0.75
    gered
    0.74
     offend
    0.72
    error
    0.71
    Activations Density 0.019%

    No Known Activations