© 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. 10-RES-JB
    11. 24016
    Prev
    Next
    INDEX
    Explanations

    expression of regret or apology

    oai_token-act-pair · gpt-3.5-turbo

    expressions of apology or regret

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Allied
    -0.74
     Bourbon
    -0.73
     Rhodes
    -0.72
     Tripoli
    -0.70
     mids
    -0.68
     RAF
    -0.67
     civilian
    -0.67
     JPEG
    -0.67
     Cincinnati
    -0.66
     Flickr
    -0.66
    POSITIVE LOGITS
    cause
    1.05
    ï¸ı
    1.03
    mean
    0.97
    âĶĢâĶĢâĶĢâĶĢ
    0.93
    thing
    0.93
    shall
    0.92
    agree
    0.92
    want
    0.92
    laughs
    0.90
    exist
    0.90
    Activations Density 0.207%

    No Known Activations