© 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. 6-RES-JB
    11. 17617
    Prev
    Next
    INDEX
    Explanations

    terms related to sports victories

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "win" and related terms in the context of victories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     encyclopedia
    -0.75
     intestine
    -0.71
     sensit
    -0.67
    senal
    -0.67
     Journals
    -0.65
     bowel
    -0.65
     notor
    -0.65
    untarily
    -0.61
    erity
    -0.60
    umn
    -0.59
    POSITIVE LOGITS
    nings
    1.32
    iem
    1.01
    now
    1.00
    throp
    0.90
    liness
    0.87
    athon
    0.82
    igan
    0.80
    watch
    0.78
    igans
    0.78
    ners
    0.77
    Activations Density 0.030%

    No Known Activations