© 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. 3147
    Prev
    Next
    INDEX
    Explanations

    information related to sports contracts and transactions

    oai_token-act-pair · gpt-3.5-turbo

    information related to sports contracts and trades

    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
     terr
    -0.79
    rika
    -0.78
     humour
    -0.78
     pulses
    -0.72
     UNESCO
    -0.72
     OPER
    -0.69
     pixels
    -0.68
    pixel
    -0.68
    emin
    -0.67
     diarr
    -0.67
    POSITIVE LOGITS
     waivers
    1.25
     undrafted
    1.13
     salary
    1.11
    signed
    1.11
     waive
    1.10
     offseason
    1.09
    Contract
    1.08
     waived
    1.07
     renegoti
    1.06
     contractual
    1.05
    Activations Density 0.894%

    No Known Activations