© 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. 6966
    Prev
    Next
    INDEX
    Explanations

    references to subscribing to receive email notifications for news stories

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "by" followed by varying contexts

    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
    naire
    -0.63
    llah
    -0.63
    Reloaded
    -0.60
     Confeder
    -0.60
    gee
    -0.59
    Í
    -0.57
    othal
    -0.56
    osterone
    -0.55
    cknow
    -0.55
    imates
    -0.55
    POSITIVE LOGITS
     subscribing
    0.94
     bookmark
    0.80
    election
    0.78
     signing
    0.77
    lined
    0.67
     subscription
    0.65
     RSS
    0.64
    joining
    0.64
    staking
    0.64
     clicking
    0.62
    Activations Density 0.012%

    No Known Activations