© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 21245
    Prev
    Next
    INDEX
    Explanations

    blog profiles and joined dates

    oai_token-act-pair · gpt-3.5-turbo

    references to online profiles and user activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andro
    -0.78
    coni
    -0.77
    agos
    -0.77
    oshenko
    -0.73
     GOODMAN
    -0.70
     Sturgeon
    -0.70
     royalty
    -0.69
    onga
    -0.68
    banks
    -0.67
    psey
    -0.66
    POSITIVE LOGITS
     Joined
    1.21
     Blog
    0.73
     AZ
    0.72
    âĸ¬
    0.72
     Posts
    0.69
    ãĥ
    0.67
     Admin
    0.64
     Beans
    0.63
     Starcraft
    0.62
    Posts
    0.62
    Activations Density 0.008%

    No Known Activations