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. 9767
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to various organizations or entities

    oai_token-act-pair · gpt-3.5-turbo

    a specific symbol or character representation in the text

    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
    anwhile
    -0.93
    theless
    -0.85
     Shutterstock
    -0.76
    etheless
    -0.71
     photoc
    -0.69
     swept
    -0.67
     fortun
    -0.66
     mete
    -0.64
     horizont
    -0.61
     transc
    -0.60
    POSITIVE LOGITS
    ¬
    1.16
    ı
    1.00
    ¡
    0.99
    Ħ¢
    0.97
    Ĵ
    0.97
    £
    0.96
    Ĥ
    0.95
    į
    0.95
    ¹
    0.94
    ľ
    0.94
    Activations Density 0.246%

    No Known Activations