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. 11-RES-JB
    6. 8880
    Prev
    Next
    INDEX
    Explanations

    terms indicating comparison or similarity

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases that express similarity

    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
     somew
    -0.78
    entially
    -0.74
    interface
    -0.68
    istical
    -0.68
    SPONSORED
    -0.67
    Published
    -0.65
     somewhere
    -0.63
    idable
    -0.63
    roximately
    -0.62
    something
    -0.60
    POSITIVE LOGITS
     ours
    1.23
     those
    1.09
    those
    1.01
     hers
    0.97
     yours
    0.93
     Those
    0.90
     ones
    0.79
    lihood
    0.76
     Cups
    0.75
     theirs
    0.73
    Activations Density 0.101%

    No Known Activations