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. 3146
    Prev
    Next
    INDEX
    Explanations

    phrases related to maintaining a line or connection

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the term "line of," particularly in various contexts

    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
    orporated
    -0.69
    é¾
    -0.65
    uca
    -0.62
    iver
    -0.62
    yi
    -0.61
    huge
    -0.61
    zu
    -0.60
    jee
    -0.60
    lot
    -0.59
    rices
    -0.57
    POSITIVE LOGITS
     scrimmage
    1.09
     succession
    1.03
     sight
    0.93
     questioning
    0.90
     reasoning
    0.81
     inquiry
    0.77
     descent
    0.75
     communication
    0.71
     Sight
    0.71
     referen
    0.71
    Activations Density 0.065%

    No Known Activations