© 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. 1-RES-JB
    11. 20195
    Prev
    Next
    INDEX
    Explanations

    phrases related to the hockey league

    oai_token-act-pair · gpt-3.5-turbo

    references to the Hockey League (HL) and its related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¯
    -0.80
    behavior
    -0.65
     Byrne
    -0.64
     Spanish
    -0.64
     Bedford
    -0.63
    within
    -0.61
    ãĥ¼ãĥĨ
    -0.61
     Romanian
    -0.60
    ta
    -0.60
    ãĤ°
    -0.59
    POSITIVE LOGITS
    HL
    1.41
     rink
    1.06
    HF
    0.99
     hockey
    0.92
    ockey
    0.87
     goaltender
    0.87
     goalt
    0.85
     puck
    0.84
    ipeg
    0.83
    ategory
    0.83
    Activations Density 0.007%

    No Known Activations