© 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 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. 9-RES-JB
    11. 20829
    Prev
    Next
    INDEX
    Explanations

    terms related to seeking, searching, striving, or pursuing a goal or objective

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to quests or searches for goals or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erva
    -0.70
    struct
    -0.63
    aution
    -0.62
    oci
    -0.60
    aura
    -0.60
    cript
    -0.60
    imated
    -0.60
    vae
    -0.58
    ector
    -0.57
    ocument
    -0.57
    POSITIVE LOGITS
     anew
    0.80
     toward
    0.77
     to
    0.77
     desperately
    0.76
     for
    0.75
     vain
    0.73
     towards
    0.71
     lest
    0.71
    lessly
    0.70
    NESS
    0.69
    Activations Density 0.168%

    No Known Activations