© 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. 20706
    Prev
    Next
    INDEX
    Explanations

    statements or opinions embedded within commas or parentheses

    oai_token-act-pair · gpt-3.5-turbo

    phrases that discuss motives and actions related to groups or individuals in societal contexts

    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
    soType
    -0.71
    conom
    -0.65
    politics
    -0.64
    aminer
    -0.64
    road
    -0.62
    ascript
    -0.62
    Stats
    -0.59
    omics
    -0.59
    interrupted
    -0.58
    URL
    -0.58
    POSITIVE LOGITS
     them
    1.11
    they
    1.08
     these
    1.08
     they
    1.06
    them
    0.96
    Their
    0.95
     their
    0.92
    They
    0.92
    their
    0.91
    these
    0.90
    Activations Density 0.690%

    No Known Activations