© 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. 9-RES-JB
    11. 18403
    Prev
    Next
    INDEX
    Explanations

    words related to excuses or justifications

    oai_token-act-pair · gpt-3.5-turbo

    terms related to justifications or rationalizations, particularly focusing on "excuses."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emouth
    -0.80
    acid
    -0.80
    marks
    -0.78
    mark
    -0.78
    itals
    -0.77
    tein
    -0.77
    ipeg
    -0.75
    utenberg
    -0.73
    weeney
    -0.72
    semble
    -0.71
    POSITIVE LOGITS
     excuse
    1.13
     excuses
    1.04
     why
    1.02
     WHY
    1.00
    abl
    0.87
     rationale
    0.84
     explanations
    0.79
     justifying
    0.78
     explanation
    0.78
    why
    0.76
    Activations Density 0.056%

    No Known Activations