© 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. 9416
    Prev
    Next
    INDEX
    Explanations

    references to sports teams, particularly the Lakers and Knicks

    oai_token-act-pair · gpt-3.5-turbo

    mentions of professional basketball teams, specifically the Lakers and Knicks

    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
    lying
    -0.85
    nels
    -0.73
    lly
    -0.67
    autical
    -0.63
    ravings
    -0.63
    ablishment
    -0.63
    lishes
    -0.62
    umbn
    -0.61
    schild
    -0.61
    remlin
    -0.60
    POSITIVE LOGITS
     Lakers
    1.05
     Clippers
    0.85
     Bryant
    0.82
    orian
    0.80
     Hots
    0.78
     Haram
    0.70
     Basketball
    0.70
    Lens
    0.70
    Zone
    0.69
     basketball
    0.69
    Activations Density 0.008%

    No Known Activations