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. 5658
    Prev
    Next
    INDEX
    Explanations

    specific code-like syntax patterns

    oai_token-act-pair · gpt-3.5-turbo

    quantitative data or statistics

    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
     treaty
    -0.69
     frontline
    -0.67
    xual
    -0.63
     behaviour
    -0.63
     scrap
    -0.63
     abolished
    -0.63
     grop
    -0.62
     unconditional
    -0.62
     favoured
    -0.61
     lasted
    -0.60
    POSITIVE LOGITS
    RAW
    1.03
    Reviewer
    1.01
    Asset
    1.00
    Topic
    0.96
    Advertisements
    0.95
    Topics
    0.95
    ------------------------
    0.92
    Package
    0.92
    Posted
    0.92
    --------------------------------------------------------
    0.91
    Activations Density 0.461%

    No Known Activations