© 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
    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. 22357
    Prev
    Next
    INDEX
    Explanations

    contractions and possessive forms

    oai_token-act-pair · gpt-3.5-turbo

    special characters or typographical anomalies in 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
    ipel
    -0.86
    assetsadobe
    -0.75
    arov
    -0.72
    ogical
    -0.72
    igious
    -0.72
    ogl
    -0.70
    è¦ļéĨĴ
    -0.68
    agos
    -0.68
    odium
    -0.67
    owan
    -0.66
    POSITIVE LOGITS
    \\\\\\\\\\\\\\\\
    0.79
    ve
    0.74
    âĤ¬
    0.72
    ll
    0.71
    VE
    0.71
     ll
    0.70
    s
    0.69
    ses
    0.67
    thens
    0.67
    meric
    0.66
    Activations Density 0.076%

    No Known Activations