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. 4-RES-JB
    6. 8643
    Prev
    Next
    INDEX
    Explanations

    acronyms followed by numbers

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to episodic content and fan engagement in media

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

    No Comments

    Negative Logits
    \'
    -0.67
    sa
    -0.63
    uni
    -0.62
    roy
    -0.61
    cig
    -0.61
    vette
    -0.61
    ÃŃs
    -0.60
    fer
    -0.60
     Patterson
    -0.59
    mk
    -0.59
    POSITIVE LOGITS
     Thumbnails
    0.72
    ebin
    0.68
     Details
    0.66
     Calculator
    0.64
    BACK
    0.62
     Removal
    0.62
    itionally
    0.61
    stals
    0.60
    Offline
    0.60
     Conditions
    0.60
    Activations Density 0.494%

    No Known Activations