© 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. 11-RES-JB
    11. 10133
    Prev
    Next
    INDEX
    Explanations

    statements indicating a temporary situation or requirement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conditions or actions that are on hold or pending until certain requirements are met

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gling
    -0.75
     underest
    -0.73
     understatement
    -0.71
     alias
    -0.69
    <?
    -0.68
     underestimate
    -0.67
     hesitate
    -0.65
     preferring
    -0.63
     fascination
    -0.63
     wasting
    -0.62
    POSITIVE LOGITS
     stabilized
    0.87
     satisfactory
    0.85
    reviewed
    0.81
     corrected
    0.80
     completes
    0.80
     clarified
    0.78
     improves
    0.76
     verified
    0.76
    fixes
    0.75
     resolved
    0.74
    Activations Density 0.182%

    No Known Activations