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. 7-RES-JB
    6. 7131
    Prev
    Next
    INDEX
    Explanations

    topics related to education and learning

    oai_token-act-pair · gpt-3.5-turbo

    significant terms related to various forms of learning and economic transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    untled
    -0.74
    imately
    -0.71
    ...]
    -0.66
    actionDate
    -0.65
    vell
    -0.60
    ollo
    -0.58
    felt
    -0.58
     sidx
    -0.58
    ËĪ
    -0.58
     Sapphire
    -0.58
    POSITIVE LOGITS
    vironments
    0.75
     alike
    0.70
     ("
    0.68
    £ı
    0.62
     (.
    0.62
    aments
    0.61
    utics
    0.60
    asia
    0.58
    ancies
    0.58
     âľĵ
    0.57
    Activations Density 0.675%

    No Known Activations