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. 0-RES-JB
    6. 124
    Prev
    Next
    INDEX
    Explanations

    references to the act of founding or establishment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of "founding" or establishment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Match
    -0.72
    motion
    -0.69
    range
    -0.68
    rated
    -0.66
    cheat
    -0.66
    anges
    -0.65
     Hazard
    -0.64
    ud
    -0.61
    Ware
    -0.60
     mirrors
    -0.58
    POSITIVE LOGITS
     founding
    3.56
     Founding
    2.58
     founders
    2.15
     founder
    1.62
     Founders
    1.55
     Founder
    1.37
     inception
    1.30
    founder
    1.30
     pioneers
    1.29
     founded
    1.21
    Activations Density 0.016%

    No Known Activations