© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 23216
    Prev
    Next
    INDEX
    Explanations

    phrases or keywords related to the importance or significance of various matters

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significance and importance in various contexts

    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
    idav
    -0.77
    adan
    -0.73
    auga
    -0.70
    assed
    -0.68
    pez
    -0.66
    xit
    -0.65
    yne
    -0.65
     Dancing
    -0.65
     IMAGES
    -0.64
     Masquerade
    -0.64
    POSITIVE LOGITS
     importance
    1.74
     significance
    1.54
     relevance
    1.54
     concern
    1.28
     interest
    1.25
     consequence
    1.24
    interest
    1.17
     urgency
    1.12
     usefulness
    1.05
    import
    1.05
    Activations Density 0.102%

    No Known Activations