© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 17588
    Prev
    Next
    INDEX
    Explanations

    names containing the substring "Sch"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Sch" or associated names within the text

    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
     responsible
    -0.71
     futures
    -0.66
     Yuri
    -0.65
     Grizzlies
    -0.63
     responsive
    -0.63
     Korra
    -0.63
     Georgian
    -0.61
     professionally
    -0.61
     Lithuan
    -0.59
     Aval
    -0.59
    POSITIVE LOGITS
    ulz
    1.46
    izophren
    1.45
    izoph
    1.40
    mitt
    1.36
    umann
    1.33
    afer
    1.28
    oen
    1.28
    acht
    1.27
    uler
    1.27
    utz
    1.24
    Activations Density 0.023%

    No Known Activations