© 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. 0-RES-JB
    11. 8396
    Prev
    Next
    INDEX
    Explanations

    instances of something failing

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "failed."

    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
     accompan
    -0.77
    eous
    -0.76
    oooo
    -0.68
    ivan
    -0.68
     arrang
    -0.68
    pour
    -0.67
    laughs
    -0.66
    âĻ
    -0.66
    adays
    -0.65
    robe
    -0.63
    POSITIVE LOGITS
     failed
    3.55
    failed
    2.91
     Failed
    2.22
     fails
    2.16
     fail
    2.06
     failing
    2.00
     botched
    1.94
     failure
    1.92
     failures
    1.87
     unsuccessful
    1.81
    Activations Density 0.015%

    No Known Activations