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. 8-RES-JB
    6. 20755
    Prev
    Next
    INDEX
    Explanations

    phrases related to textual formatting or special characters

    oai_token-act-pair · gpt-3.5-turbo

    symbols and characters that represent emoticons or special formatting

    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
     Mous
    -0.90
     shroud
    -0.80
     sling
    -0.78
     Sabha
    -0.77
     coerc
    -0.73
     shack
    -0.71
     dispers
    -0.71
     Belg
    -0.70
     ASC
    -0.70
     assemb
    -0.67
    POSITIVE LOGITS
    ľ
    1.83
    ¡
    1.33
    Ľ
    1.21
    Ķ
    1.21
    ª
    1.20
    ł
    1.19
    ĺ
    1.14
    ®
    1.13
    ¦
    1.11
    ļ
    1.11
    Activations Density 0.270%

    No Known Activations