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. 3-RES-JB
    6. 11809
    Prev
    Next
    INDEX
    Explanations

    domain-specific terms related to computing and the internet

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Net" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é»Ĵ
    -0.77
    «ĺ
    -0.71
    DragonMagazine
    -0.70
    æł
    -0.68
    å°Ĩ
    -0.67
    axter
    -0.67
    =-=-=-=-
    -0.67
    interstitial
    -0.67
    åĪ
    -0.66
    sbm
    -0.65
    POSITIVE LOGITS
    anyahu
    1.31
    izens
    1.16
    izen
    1.16
    aji
    0.94
    working
    0.89
    runner
    0.89
    tle
    0.88
    sov
    0.82
    roots
    0.81
    rw
    0.80
    Activations Density 0.009%

    No Known Activations