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. 16346
    Prev
    Next
    INDEX
    Explanations

    height and weight measurements

    oai_token-act-pair · gpt-3.5-turbo

    specific measurements and weight-related information about individuals

    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
    hement
    -0.72
    ulner
    -0.69
    ãĥĥ
    -0.68
     Wast
    -0.66
    nex
    -0.65
    nces
    -0.65
     Administ
    -0.64
     QC
    -0.63
    isky
    -0.63
     Mub
    -0.61
    POSITIVE LOGITS
     lim
    0.70
     lumber
    0.69
     braces
    0.67
    llan
    0.67
     diameter
    0.67
    ï¸ı
    0.66
     pedals
    0.65
    pload
    0.64
    veland
    0.63
    imble
    0.63
    Activations Density 0.137%

    No Known Activations