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. 17280
    Prev
    Next
    INDEX
    Explanations

    references to media information such as news sources and social media accounts

    oai_token-act-pair · gpt-3.5-turbo

    various punctuation marks and formatting indicators suggesting visual content or emphasis

    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
    ©¶æ
    -0.66
    maxwell
    -0.61
    geries
    -0.61
     Classics
    -0.60
    eln
    -0.60
    xual
    -0.58
     Ard
    -0.58
     Petra
    -0.57
     retiring
    -0.56
     Rolls
    -0.56
    POSITIVE LOGITS
    ³³³³
    0.90
    Introduced
    0.81
    Original
    0.78
    Advertisements
    0.76
    Previously
    0.75
    RELATED
    0.74
    Letter
    0.74
    ________________________________________________________________
    0.73
    Madison
    0.73
    ONSORED
    0.73
    Activations Density 0.179%

    No Known Activations