© 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. 8-RES-JB
    11. 8994
    Prev
    Next
    INDEX
    Explanations

    specific dates in the format "Month Day, Year"

    oai_token-act-pair · gpt-3.5-turbo

    sentence endings and punctuation marks indicating the conclusion of thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     laugh
    -0.79
     mach
    -0.79
     imperson
    -0.79
     affili
    -0.77
     hats
    -0.73
     pretended
    -0.72
     imitation
    -0.72
    roph
    -0.72
     mustache
    -0.72
     complimentary
    -0.71
    POSITIVE LOGITS
     Since
    1.07
     During
    1.05
     However
    1.04
     Its
    0.99
     Until
    0.99
     Previously
    0.98
     Assuming
    0.97
     Therefore
    0.97
     Shortly
    0.95
     Consequently
    0.95
    Activations Density 0.534%

    No Known Activations