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. 5530
    Prev
    Next
    INDEX
    Explanations

    phrases related to upholstery or furniture design

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of "holistic."

    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
    EED
    -0.76
     fierce
    -0.67
     Fang
    -0.62
     Cly
    -0.60
    ngth
    -0.59
     Eag
    -0.58
    FUL
    -0.58
    XL
    -0.57
    hips
    -0.55
     exponentially
    -0.54
    POSITIVE LOGITS
    ocaust
    1.25
    idays
    1.18
    stery
    0.97
    tering
    0.93
    itaire
    0.93
    mes
    0.92
    phe
    0.87
    spection
    0.86
    ters
    0.85
    icz
    0.84
    Activations Density 0.025%

    No Known Activations