© 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. 2946
    Prev
    Next
    INDEX
    Explanations

    references to actions involving a sports ball, particularly in a tactical or strategic context

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

    references to the ball, puck, or ball-related actions in sports 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
     Flavoring
    -0.77
     Beef
    -0.71
     Nob
    -0.69
     Veg
    -0.68
     Annex
    -0.67
     Cind
    -0.67
     plur
    -0.66
     Nobel
    -0.66
     Magicka
    -0.66
     Thor
    -0.64
    POSITIVE LOGITS
     carrier
    1.25
    handler
    1.19
     handler
    1.00
     carriers
    0.93
    car
    0.92
    hand
    0.89
    club
    0.89
    wash
    0.88
    istics
    0.85
    hawk
    0.84
    Activations Density 0.051%

    No Known Activations