Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 8072
    Prev
    Next
    INDEX
    Explanations

    statements or conditions indicating a temporary hold or suspension of activities

    oai_token-act-pair · gpt-3.5-turbo

    references to conditions or situations that are pending resolution or require a subsequent action

    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
     lur
    -0.72
    <?
    -0.71
     disbelief
    -0.69
     fearing
    -0.68
     Variant
    -0.67
     understatement
    -0.66
     alias
    -0.62
     wasting
    -0.62
    gling
    -0.61
     grinning
    -0.60
    POSITIVE LOGITS
     completes
    0.97
     clears
    0.93
     recovers
    0.92
     sufficiently
    0.85
     satisfactory
    0.83
     finishes
    0.82
     cleared
    0.80
     expires
    0.79
     reaches
    0.78
     stabilized
    0.77
    Activations Density 0.295%

    No Known Activations