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. 0-RES-JB
    6. 24167
    Prev
    Next
    INDEX
    Explanations

    words related to specific types of lizards named "gecko"

    oai_token-act-pair · gpt-3.5-turbo

    specific species names, particularly reptiles and mammals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    actionDate
    -0.76
    Parameter
    -0.75
    åħ
    -0.73
    ages
    -0.72
    RA
    -0.71
     sab
    -0.70
     Braz
    -0.70
     reper
    -0.70
    dies
    -0.69
    NetMessage
    -0.69
    POSITIVE LOGITS
    cko
    4.44
    ovan
    1.31
    hog
    1.10
     DK
    1.04
    ffen
    0.98
    yip
    0.97
    KO
    0.95
    keleton
    0.93
    okin
    0.93
    eme
    0.93
    Activations Density 0.038%

    No Known Activations