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. 6-RES-JB
    6. 24116
    Prev
    Next
    INDEX
    Explanations

    words related to projects and programs

    oai_token-act-pair · gpt-3.5-turbo

    references to specific projects or programs, particularly those related to research and development initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    veland
    -0.73
     wedge
    -0.71
     corners
    -0.70
     cand
    -0.67
     Finn
    -0.66
     spoilers
    -0.66
     margin
    -0.65
     hairs
    -0.65
    lder
    -0.64
     Cort
    -0.64
    POSITIVE LOGITS
     undertaken
    1.13
     underway
    1.04
     funded
    1.01
     billed
    0.89
     financed
    0.88
     spearheaded
    0.87
     chaired
    0.85
    yrinth
    0.84
    funded
    0.84
     overseen
    0.83
    Activations Density 0.430%

    No Known Activations