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. 2-RES-JB
    6. 10836
    Prev
    Next
    INDEX
    Explanations

    names of authors or contributors at the beginning of an article or piece of content

    oai_token-act-pair · gpt-3.5-turbo

    mentions of authors or individuals associated with written works or articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sic
    -0.77
    coni
    -0.74
     derog
    -0.70
    nown
    -0.67
     externalToEVAOnly
    -0.66
     successors
    -0.66
    jri
    -0.65
     disg
    -0.64
     bis
    -0.64
     hereafter
    -0.64
    POSITIVE LOGITS
     Updated
    0.90
     Vegan
    0.85
    zbollah
    0.83
    CLUS
    0.82
     Expand
    0.79
     âĢº
    0.79
    WASHINGTON
    0.75
     UPDATE
    0.74
    Welcome
    0.73
     Calculator
    0.73
    Activations Density 0.915%

    No Known Activations