© 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. 13210
    Prev
    Next
    INDEX
    Explanations

    words related to specific sports leagues and events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various hockey leagues and competitions

    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
     ali
    -0.71
     posture
    -0.70
    schild
    -0.66
     frontman
    -0.64
     gorilla
    -0.64
     graphene
    -0.63
    ued
    -0.63
     selfies
    -0.63
     answ
    -0.63
     bombard
    -0.63
    POSITIVE LOGITS
    League
    1.32
     Division
    1.12
     League
    1.10
     Cup
    1.09
     Championship
    1.07
    Draft
    1.05
     Conference
    1.04
     Championships
    1.03
     Playoffs
    1.02
     Colleg
    1.00
    Activations Density 0.154%

    No Known Activations