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. 15039
    Prev
    Next
    INDEX
    Explanations

    words related to statistics and mathematical concepts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "mean" in various statistical contexts

    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
    taboola
    -0.85
    DOM
    -0.81
    thumbnails
    -0.75
    adr
    -0.74
    SOURCE
    -0.74
    aware
    -0.72
    ailable
    -0.71
    anon
    -0.69
     VIDEOS
    -0.68
    ucha
    -0.67
    POSITIVE LOGITS
     spirited
    0.83
    ings
    0.71
    eth
    0.68
    eway
    0.68
    aign
    0.66
     goodbye
    0.65
    ening
    0.63
    ãĥĥãĤ¯
    0.63
    erest
    0.62
    nova
    0.60
    Activations Density 0.015%

    No Known Activations