© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7264
    Prev
    Next
    INDEX
    Explanations

    mentions of specific hockey-related terms and entities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to hockey and its associated league

    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
     GOODMAN
    -0.72
    ibility
    -0.71
    =-=-=-=-=-=-=-=-
    -0.70
    ciating
    -0.68
    agy
    -0.63
    iannopoulos
    -0.63
    ible
    -0.63
    ARC
    -0.62
    course
    -0.61
     Beir
    -0.60
    POSITIVE LOGITS
     rink
    1.07
     defenseman
    0.91
    ipeg
    0.91
     goalie
    0.86
     goaltender
    0.84
     hockey
    0.83
     puck
    0.82
     goalt
    0.81
    ockey
    0.80
    emi
    0.76
    Activations Density 0.139%

    No Known Activations