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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 10739
    Prev
    Next
    INDEX
    Explanations

    references to the basketball player Russell Westbrook

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Russell."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    glers
    -0.91
    alach
    -0.74
    bid
    -0.72
    choes
    -0.71
    board
    -0.68
    bered
    -0.66
    onies
    -0.66
    lda
    -0.65
    geries
    -0.65
    urses
    -0.65
    POSITIVE LOGITS
     Westbrook
    1.05
     Wilson
    0.90
     Brand
    0.85
     Peters
    0.85
    minster
    0.83
    ian
    0.82
     Sage
    0.81
    oid
    0.76
    ians
    0.74
    ville
    0.73
    Activations Density 0.027%

    No Known Activations