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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 6002
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing detailed explanations or descriptions about various topics

    oai_token-act-pair · gpt-3.5-turbo

    references to accounts or explanations related to various subjects

    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
    NetMessage
    -0.73
     cour
    -0.65
     Jinn
    -0.63
    GGGGGGGG
    -0.62
     Niet
    -0.61
     Oval
    -0.61
     Aki
    -0.60
     Toys
    -0.59
     Wings
    -0.58
    JV
    -0.58
    POSITIVE LOGITS
    ancy
    1.12
    abilities
    1.00
     accounts
    0.99
     balances
    0.97
    Account
    0.95
    account
    0.89
     rece
    0.88
     account
    0.87
    books
    0.87
     Accounts
    0.86
    Activations Density 0.019%

    No Known Activations