Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 17392
    Prev
    Next
    INDEX
    Explanations

    specific symbols or characters in a text document, namely a particular arrow symbol

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "âĢ"

    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
     Tid
    -0.70
     Belt
    -0.67
    ggies
    -0.67
     Bris
    -0.66
     coasts
    -0.64
    ansas
    -0.63
     Sic
    -0.62
     Leban
    -0.61
     playbook
    -0.61
     Libyan
    -0.61
    POSITIVE LOGITS
    ¡
    1.19
    ¬
    1.18
    º
    1.10
    ¹
    1.04
    £
    1.03
    »
    1.02
    į
    1.00
    ³
    0.99
    ¿
    0.98
    Į
    0.98
    Activations Density 0.368%

    No Known Activations