© 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. 20121
    Prev
    Next
    INDEX
    Explanations

    NBA-related terms and player names

    oai_token-act-pair · gpt-3.5-turbo

    names of basketball players and references to basketball-related actions

    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
     resort
    -0.66
    lear
    -0.66
    cht
    -0.65
    netflix
    -0.65
     puppet
    -0.64
    ordering
    -0.63
     scal
    -0.62
     overriding
    -0.61
    arten
    -0.60
    ttle
    -0.60
    POSITIVE LOGITS
     Nuggets
    0.95
     Thib
    0.91
    NBA
    0.91
     Pacers
    0.91
    asketball
    0.88
     Harden
    0.84
     Hornets
    0.83
     Timberwolves
    0.83
     Raptors
    0.80
     Wiggins
    0.79
    Activations Density 0.039%

    No Known Activations