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. 19452
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something is unique or specific

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating specificity and uniqueness in relation to various contexts

    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
     largeDownload
    -0.76
    rio
    -0.75
    DragonMagazine
    -0.73
    sterdam
    -0.70
    rolled
    -0.70
    hur
    -0.68
    Written
    -0.67
    pard
    -0.66
     pairs
    -0.65
    ivated
    -0.65
    POSITIVE LOGITS
    ggles
    0.93
    pper
    0.73
     perfection
    0.71
    cffff
    0.69
     attain
    0.69
     Virtue
    0.68
     shore
    0.68
     withstand
    0.67
     behold
    0.66
    ppers
    0.66
    Activations Density 0.166%

    No Known Activations