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. 1511
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or processes unfolding over time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating progression or unfolding events

    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
    £ı
    -0.77
    ¿½
    -0.76
    umn
    -0.71
    Ħ¢
    -0.69
    ertation
    -0.68
    arthed
    -0.68
    ģĸ
    -0.67
    İ
    -0.66
    ensable
    -0.64
    cci
    -0.61
    POSITIVE LOGITS
     volleyball
    0.70
     veto
    0.70
     chess
    0.68
     captcha
    0.67
     Bowl
    0.67
     drums
    0.66
     Tradable
    0.66
    ¢
    0.65
    itaire
    0.65
     poker
    0.65
    Activations Density 0.442%

    No Known Activations