© 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. 7-RES-JB
    11. 10870
    Prev
    Next
    INDEX
    Explanations

    words related to sports positions and playing surfaces

    oai_token-act-pair · gpt-3.5-turbo

    references to sports locations or playing surfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IRD
    -0.76
    laus
    -0.71
    anus
    -0.68
    achus
    -0.66
    ortium
    -0.66
    oras
    -0.65
    ancial
    -0.63
    anson
    -0.63
    omin
    -0.63
    ett
    -0.62
    POSITIVE LOGITS
    plays
    0.75
     podium
    0.72
    keeper
    0.70
    tests
    0.69
    waves
    0.69
     persona
    0.65
    walker
    0.63
    places
    0.63
    keepers
    0.62
     coach
    0.62
    Activations Density 0.081%

    No Known Activations