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. 0-RES-JB
    6. 3831
    Prev
    Next
    INDEX
    Explanations

    names or terms related to the Suez Canal

    oai_token-act-pair · gpt-3.5-turbo

    references to the Suez Canal

    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
     Killer
    -0.71
     decor
    -0.69
     killer
    -0.69
     shr
    -0.68
     Max
    -0.66
     Minimum
    -0.64
    SN
    -0.63
     form
    -0.63
    min
    -0.62
     Keith
    -0.61
    POSITIVE LOGITS
    uez
    5.34
    hetti
    1.21
    riz
    1.10
    uese
    1.10
    ued
    1.09
    omez
    1.08
    ues
    1.06
    ierrez
    1.06
    enez
    1.03
    uel
    1.00
    Activations Density 0.012%

    No Known Activations