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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 9334
    Prev
    Next
    INDEX
    Explanations

    mention of the sport of hockey

    oai_token-act-pair · gpt-3.5-turbo

    references to hockey and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibility
    -0.79
    graded
    -0.79
    iments
    -0.69
    ateral
    -0.69
    ablishment
    -0.68
    iary
    -0.67
    iment
    -0.65
    apsed
    -0.65
    utter
    -0.65
    ige
    -0.65
    POSITIVE LOGITS
     rink
    1.35
     hockey
    1.22
     puck
    1.09
    ockey
    0.98
    ipeg
    0.95
     goalie
    0.90
     Hockey
    0.90
     skating
    0.86
    soDeliveryDate
    0.81
     goaltender
    0.81
    Activations Density 0.009%

    No Known Activations