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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 8418
    Prev
    Next
    INDEX
    Explanations

    references to the sports team "Huskies"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the "Huskies" team or variations of the name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    afort
    -0.77
     Scotia
    -0.77
    inez
    -0.69
     sheet
    -0.68
    ourning
    -0.68
     clearance
    -0.67
    oulos
    -0.61
     dividing
    -0.61
    eering
    -0.60
     chance
    -0.60
    POSITIVE LOGITS
    kies
    1.21
    bands
    1.17
    band
    1.14
    ayn
    1.05
    ky
    1.04
    qv
    1.03
    ®
    1.00
    ¦
    0.98
    sein
    0.98
    kie
    0.96
    Activations Density 0.017%

    No Known Activations