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. 1-RES-JB
    6. 12100
    Prev
    Next
    INDEX
    Explanations

    highly specific terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    elements related to colloquial language or informal expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     RSA
    -0.70
     psyche
    -0.63
     Hearts
    -0.61
     absorbing
    -0.60
     sexes
    -0.60
     Tate
    -0.57
     conscience
    -0.57
     guiActiveUnfocused
    -0.56
     discriminating
    -0.55
     infiltrate
    -0.54
    POSITIVE LOGITS
    oqu
    1.33
    naire
    0.86
    BuyableInstoreAndOnline
    0.84
    atl
    0.82
    ial
    0.81
    inet
    0.81
    DragonMagazine
    0.80
    oons
    0.79
    arin
    0.79
    ially
    0.79
    Activations Density 0.012%

    No Known Activations