© 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. 12-RES-JB
    11. 3623
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and player evaluations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    descriptors related to exceptional talent or performance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    attribute
    -0.76
    ãĥ¯ãĥ³
    -0.70
    gency
    -0.68
    ADRA
    -0.67
    kat
    -0.65
    CHAT
    -0.65
    pmwiki
    -0.64
    Accessory
    -0.63
    ritical
    -0.62
     srfAttach
    -0.61
    POSITIVE LOGITS
     alive
    1.34
     imaginable
    0.97
     ever
    0.94
     Alive
    0.94
     around
    0.88
     in
    0.87
     afloat
    0.87
     anywhere
    0.83
     EVER
    0.81
     on
    0.75
    Activations Density 0.155%

    No Known Activations