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. 3-RES-JB
    6. 8579
    Prev
    Next
    INDEX
    Explanations

    numerical values related to large quantities or groups

    oai_token-act-pair · gpt-3.5-turbo

    references to millennials and their experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lde
    -0.78
     slack
    -0.64
     yours
    -0.63
     pool
    -0.63
     tang
    -0.62
     Syndicate
    -0.62
     Annotations
    -0.62
     stern
    -0.62
     vain
    -0.61
     fitting
    -0.61
    POSITIVE LOGITS
    enium
    1.29
    enn
    1.22
    ennial
    1.19
    imet
    1.19
    iday
    1.10
    isec
    1.02
    icent
    0.99
    imeter
    0.94
    oton
    0.93
    ENN
    0.91
    Activations Density 0.007%

    No Known Activations