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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6365
    Prev
    Next
    INDEX
    Explanations

    words related to sports contracts and player movements

    oai_token-act-pair · gpt-3.5-turbo

    the future tense auxiliary verb "will."

    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
    soType
    -0.83
    76561
    -0.80
    izoph
    -0.73
     Advertisement
    -0.72
    hea
    -0.66
    engineering
    -0.66
    MpServer
    -0.65
     interven
    -0.64
    Newsletter
    -0.62
    cond
    -0.61
    POSITIVE LOGITS
     undoubtedly
    1.11
     likely
    1.10
     surely
    1.09
     be
    1.06
     undergo
    1.05
     doubtless
    1.04
     compete
    1.01
     revert
    1.00
     inherit
    0.99
     join
    0.96
    Activations Density 0.147%

    No Known Activations