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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 13481
    Prev
    Next
    INDEX
    Explanations

    names or terms related to specific people or places

    oai_token-act-pair · gpt-3.5-turbo

    suffixes related to adjectives and adverbs

    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
    arians
    -0.72
    aciously
    -0.70
    isable
    -0.70
    izable
    -0.69
    icide
    -0.65
    ually
    -0.65
    ifying
    -0.64
    IBLE
    -0.62
     elig
    -0.62
    iful
    -0.61
    POSITIVE LOGITS
    tics
    1.24
    mph
    1.18
    eah
    1.17
    tsky
    1.12
    lene
    1.11
    nn
    1.10
    rics
    1.09
    dd
    1.05
    tes
    1.03
    ea
    1.03
    Activations Density 0.154%

    No Known Activations