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. 7-RES-JB
    6. 14916
    Prev
    Next
    INDEX
    Explanations

    names, terms, and references that are common in written text

    oai_token-act-pair · gpt-3.5-turbo

    the recurring word "also."

    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
    athi
    -0.75
    agus
    -0.74
    liest
    -0.73
    adden
    -0.68
    crow
    -0.64
    etime
    -0.62
    anwhile
    -0.62
    animate
    -0.61
    endar
    -0.61
    rect
    -0.60
    POSITIVE LOGITS
     known
    0.87
     referred
    0.85
     includes
    0.84
     included
    0.80
     spelled
    0.78
     contains
    0.78
     Accessed
    0.75
    roph
    0.72
    pmwiki
    0.71
     served
    0.71
    Activations Density 0.096%

    No Known Activations