Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 11-RES-JB
    6. 10858
    Prev
    Next
    INDEX
    Explanations

    comparisons of different states or conditions between past and present

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases indicating change over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Expand
    -0.54
    Phill
    -0.53
    erous
    -0.51
    uckland
    -0.51
    ococ
    -0.51
    ouse
    -0.51
    ango
    -0.50
    skirts
    -0.49
    rf
    -0.48
    ouses
    -0.48
    POSITIVE LOGITS
     before
    0.89
     twenty
    0.89
     fifteen
    0.89
     thirty
    0.85
     fifty
    0.85
     ages
    0.84
     forty
    0.83
     ten
    0.83
     20
    0.82
     eight
    0.79
    Activations Density 0.121%

    No Known Activations