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. 3-RES-JB
    6. 19970
    Prev
    Next
    INDEX
    Explanations

    large groups of entities operating together for a common purpose

    oai_token-act-pair · gpt-3.5-turbo

    mentions of consortiums and related organizational structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    natal
    -0.69
    birds
    -0.69
    flation
    -0.66
    Gun
    -0.65
    vae
    -0.64
    fly
    -0.63
    doors
    -0.63
    Adv
    -0.62
    wards
    -0.59
     Extrem
    -0.59
    POSITIVE LOGITS
     consortium
    1.07
    ortium
    1.06
     Consortium
    1.02
    ecided
    0.74
     GOODMAN
    0.73
    ECA
    0.71
    members
    0.70
     orchestr
    0.69
    ele
    0.69
     members
    0.68
    Activations Density 0.011%

    No Known Activations