© 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. 8-RES-JB
    11. 3359
    Prev
    Next
    INDEX
    Explanations

    sponsorship agreements or partnerships between different entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sponsorship and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icators
    -0.78
     selves
    -0.77
     inexper
    -0.69
     ages
    -0.68
     piled
    -0.67
     aged
    -0.66
    ife
    -0.65
     horm
    -0.65
     lad
    -0.64
    gery
    -0.64
    POSITIVE LOGITS
     Cosponsors
    0.95
    DAQ
    0.83
     supplying
    0.76
    arget
    0.74
     TRI
    0.73
    FACE
    0.72
     Investor
    0.71
     UNESCO
    0.71
     NAFTA
    0.71
    ETS
    0.69
    Activations Density 0.619%

    No Known Activations