© 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. 10-RES-JB
    11. 3392
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming languages and concepts, specifically focusing on Python and C++

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to programming languages and technology concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assis
    -0.83
    Joined
    -0.76
     Amid
    -0.75
    âĢİ
    -0.73
    女
    -0.72
     Salman
    -0.71
    actionDate
    -0.67
     Belfast
    -0.66
    appa
    -0.66
     ..........
    -0.64
    POSITIVE LOGITS
     uses
    1.35
     recommends
    1.31
     tends
    1.20
     relies
    1.20
     prefers
    1.19
     utilizes
    1.19
     forbids
    1.18
     allows
    1.17
     defines
    1.15
     encourages
    1.15
    Activations Density 0.523%

    No Known Activations