© 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. 6607
    Prev
    Next
    INDEX
    Explanations

    phrases related to reading or continuing written content, notably using the word "Continue."

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to continuation or ongoing 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
    axter
    -0.66
    arial
    -0.66
    warts
    -0.62
    REF
    -0.62
    lain
    -0.62
    oult
    -0.60
    doms
    -0.59
    ulz
    -0.57
    knife
    -0.57
    ouls
    -0.56
    POSITIVE LOGITS
     scrolling
    0.89
     Reading
    0.85
     reading
    0.81
     Below
    0.73
     clicking
    0.67
     submitting
    0.63
     Thumbnails
    0.63
     Shopping
    0.61
     trending
    0.61
     Sketch
    0.61
    Activations Density 0.007%

    No Known Activations