© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 2644
    Prev
    Next
    INDEX
    Explanations

    words related to weight classes in sports, specifically focusing on the welterweight division

    oai_token-act-pair · gpt-3.5-turbo

    terms related to weight classes in combat sports

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

    No Comments

    Negative Logits
    agate
    -0.77
    uters
    -0.75
    udi
    -0.74
    uyomi
    -0.72
    imately
    -0.68
    avorite
    -0.68
    reath
    -0.66
    ADRA
    -0.65
    roma
    -0.65
    oglu
    -0.65
    POSITIVE LOGITS
    nut
    0.99
    nuts
    0.89
     wel
    0.89
    forth
    0.84
    some
    0.84
    tered
    0.83
    swer
    0.82
    cour
    0.80
    wear
    0.79
    tering
    0.76
    Activations Density 0.026%

    No Known Activations