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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 404
    Prev
    Next
    INDEX
    Explanations

    terms related to airflow and air conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to air

    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
     Cla
    -0.76
    orkshire
    -0.72
    enance
    -0.68
     Barcl
    -0.67
     Ll
    -0.66
    llan
    -0.66
     Kuh
    -0.66
     Saur
    -0.66
     McKin
    -0.64
    achu
    -0.62
    POSITIVE LOGITS
    waves
    1.14
    bnb
    1.01
    tight
    1.01
     conditioning
    0.95
    planes
    0.94
    bending
    0.92
     turbulence
    0.91
    plane
    0.91
     breat
    0.90
     circulation
    0.87
    Activations Density 0.021%

    No Known Activations