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. 0-RES-JB
    6. 13
    Prev
    Next
    INDEX
    Explanations

    company names or entities with "LLC" in their name

    oai_token-act-pair · gpt-3.5-turbo

    references to limited liability companies (LLCs) and limited liability partnerships (LLPs)

    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
    bishop
    -0.69
     colour
    -0.65
     poster
    -0.64
     traveller
    -0.63
     young
    -0.62
    wards
    -0.60
     emphas
    -0.60
    vis
    -0.60
    Statistics
    -0.58
     recogn
    -0.58
    POSITIVE LOGITS
     LLC
    3.83
     LLP
    2.11
     Ltd
    1.82
     Inc
    1.81
     LTD
    1.74
     INC
    1.46
     Associates
    1.25
     Holdings
    1.15
     Corp
    1.15
     LP
    1.15
    Activations Density 0.023%

    No Known Activations