© 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. 11-RES-JB
    11. 9867
    Prev
    Next
    INDEX
    Explanations

    phrases related to continuing or reading further

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to ongoing actions or instructions to read further

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oun
    -0.66
    olit
    -0.61
    opol
    -0.58
    mith
    -0.58
    Corp
    -0.58
    mart
    -0.57
    ciples
    -0.56
    knife
    -0.54
    lain
    -0.54
    é¾
    -0.54
    POSITIVE LOGITS
     reading
    0.89
     scrolling
    0.76
     Reading
    0.72
     clicking
    0.67
     submitting
    0.62
     Below
    0.61
    ...]
    0.61
     READ
    0.60
     trending
    0.59
    ceive
    0.59
    Activations Density 0.013%

    No Known Activations