© 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. 4990
    Prev
    Next
    INDEX
    Explanations

    superlatives such as "the most," "by far," "top," and "biggest."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize significance or extremity of experiences or opinions

    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
    artments
    -0.60
    irie
    -0.60
    abolic
    -0.60
    ifferent
    -0.60
    assian
    -0.59
    ascript
    -0.59
    ysis
    -0.58
    eral
    -0.58
    ignant
    -0.57
    abbling
    -0.55
    POSITIVE LOGITS
     THE
    0.97
     the
    0.95
    the
    0.94
     one
    0.93
     among
    0.81
    one
    0.79
     easiest
    0.78
     coolest
    0.77
    Britain
    0.77
     hardest
    0.76
    Activations Density 0.350%

    No Known Activations