© 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. 1-RES-JB
    11. 23979
    Prev
    Next
    INDEX
    Explanations

    keywords or phrases related to data-intensive applications

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    feeding
    -0.72
    gm
    -0.72
    *=-
    -0.68
    UCT
    -0.67
    \\\\\\\\
    -0.66
     Horus
    -0.65
    Leader
    -0.64
    Benz
    -0.64
    ãĥĦ
    -0.63
    ifa
    -0.63
    POSITIVE LOGITS
     applications
    1.55
     application
    1.23
     Applications
    1.12
    Applications
    0.99
     applic
    0.95
    afety
    0.95
     appl
    0.94
     Application
    0.89
    lication
    0.88
     apps
    0.88
    Activations Density 0.008%

    No Known Activations