© 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. 15220
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases indicating participation or involvement in a series of events or actions

    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
     Cosponsors
    -0.79
    amount
    -0.67
    icut
    -0.64
     condem
    -0.63
     confir
    -0.63
     distingu
    -0.63
    icultural
    -0.62
    hemat
    -0.62
    heses
    -0.62
     describ
    -0.61
    POSITIVE LOGITS
    icial
    0.80
     course
    0.76
    course
    0.75
    eworks
    0.70
    ounds
    0.70
    AMS
    0.61
    IFE
    0.61
    ARE
    0.61
     ours
    0.61
    OME
    0.58
    Activations Density 0.056%

    No Known Activations