© 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. 11-RES-JB
    11. 20570
    Prev
    Next
    INDEX
    Explanations

    mentions of professional sports players and team transactions

    oai_token-act-pair · gpt-3.5-turbo

    names of basketball players and their associated statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "}],"
    -0.75
    Democrats
    -0.68
    wig
    -0.67
    umbledore
    -0.66
     indic
    -0.66
    witch
    -0.66
    ento
    -0.64
     statewide
    -0.64
     owl
    -0.63
     pamphlet
    -0.62
    POSITIVE LOGITS
     Carlos
    1.23
     Kevin
    1.16
     Aaron
    1.16
     LeBron
    1.14
     Derek
    1.13
     Brandon
    1.13
     Drew
    1.12
     Lance
    1.12
     Emmanuel
    1.11
     Jeremy
    1.11
    Activations Density 0.114%

    No Known Activations