© 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. 7454
    Prev
    Next
    INDEX
    Explanations

    sentences ending with periods

    oai_token-act-pair · gpt-3.5-turbo

    sentences that indicate significant events or actions

    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
     nodd
    -0.86
     quir
    -0.83
     dared
    -0.75
     daring
    -0.73
     whiff
    -0.73
     taboo
    -0.73
     invent
    -0.72
     glim
    -0.72
     fancy
    -0.71
     rye
    -0.69
    POSITIVE LOGITS
     Accordingly
    1.37
     Therefore
    1.35
     Additionally
    1.33
     Furthermore
    1.32
     Consequently
    1.23
     Our
    1.22
     Moreover
    1.22
    âĢİ
    1.21
     âĢ¦"
    1.20
     However
    1.20
    Activations Density 0.238%

    No Known Activations