© 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. 22686
    Prev
    Next
    INDEX
    Explanations

    words related to actions or processes that continue or persist

    oai_token-act-pair · gpt-3.5-turbo

    references to ongoing situations or trends

    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
    errilla
    -0.66
    asio
    -0.64
    ographical
    -0.64
    ãĥĥãĥĪ
    -0.64
     Tycoon
    -0.63
    RN
    -0.62
    eah
    -0.61
    ilibrium
    -0.61
    ierrez
    -0.60
    reau
    -0.59
    POSITIVE LOGITS
     unab
    1.46
     ap
    1.08
     uninterrupted
    1.08
     unchecked
    1.07
     onward
    1.02
     unim
    0.96
     onwards
    0.93
     unchanged
    0.92
     indefinitely
    0.90
     unanswered
    0.87
    Activations Density 0.050%

    No Known Activations