Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 8904
    Prev
    Next
    INDEX
    Explanations

    words related to significant or outstanding achievements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sports performance and coaching dynamics

    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
    Ey
    -0.81
    raq
    -0.75
    Eva
    -0.73
     Patent
    -0.70
     Processing
    -0.69
     ISBN
    -0.69
     CBO
    -0.68
     Citation
    -0.66
    poly
    -0.66
    ophen
    -0.65
    POSITIVE LOGITS
     rookies
    1.05
     teammate
    1.04
     rookie
    1.02
     Rookie
    1.01
     teammates
    1.00
     jerseys
    0.89
     championship
    0.89
     comeback
    0.86
     newcomer
    0.86
     contenders
    0.85
    Activations Density 0.343%

    No Known Activations