© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 20323
    Prev
    Next
    INDEX
    Explanations

    email-related error messages

    oai_token-act-pair · gpt-3.5-turbo

    instances of invalid email notifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    teenth
    -0.58
     rigged
    -0.58
    lain
    -0.57
     proxies
    -0.56
     exhibits
    -0.56
     modeling
    -0.55
     endeavor
    -0.55
     coined
    -0.55
     numbered
    -0.55
    natureconservancy
    -0.54
    POSITIVE LOGITS
     Email
    0.83
     Thumbnails
    0.77
    Filter
    0.73
    Skip
    0.72
    atter
    0.70
    BuyableInstoreAndOnline
    0.69
     guiActiveUnfocused
    0.68
     srfAttach
    0.68
     Quantity
    0.67
    Sorry
    0.66
    Activations Density 0.014%

    No Known Activations