© 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. 4-RES-JB
    11. 19557
    Prev
    Next
    INDEX
    Explanations

    the names and mentions of the basketball player DeAndre Jordan

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly athletes or political figures

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

    No Comments

    Negative Logits
     srfAttach
    -0.73
    yip
    -0.71
     Vinyl
    -0.70
     Flavoring
    -0.63
     HDL
    -0.63
     bluff
    -0.61
     Boxing
    -0.60
    Based
    -0.59
    uesday
    -0.59
     agg
    -0.59
    POSITIVE LOGITS
    ciating
    0.87
    alion
    0.76
    ctions
    0.74
    enment
    0.72
    agram
    0.72
    ibles
    0.71
    ctic
    0.70
    liction
    0.69
    ction
    0.68
    heid
    0.67
    Activations Density 0.078%

    No Known Activations