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. 1-RES-JB
    6. 23745
    Prev
    Next
    INDEX
    Explanations

    text related to particular characters or names that have a unique combination of special characters

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or symbol in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cler
    -0.77
     crush
    -0.71
     entirety
    -0.66
     carriers
    -0.63
     discounted
    -0.62
     Hera
    -0.62
     holders
    -0.61
    naires
    -0.61
    clerosis
    -0.60
    idepress
    -0.60
    POSITIVE LOGITS
    å
    1.42
    sson
    1.07
    ä
    0.98
    ø
    0.96
    borg
    0.93
    ö
    0.91
    ð
    0.83
    sb
    0.82
    lund
    0.82
    sung
    0.81
    Activations Density 0.005%

    No Known Activations