© 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. 6-RES-JB
    11. 13816
    Prev
    Next
    INDEX
    Explanations

    acronyms related to organizations and projects

    oai_token-act-pair · gpt-3.5-turbo

    acronyms or abbreviations related to organizations or programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Geral
    -0.65
     Alban
    -0.65
     Gors
    -0.64
    strings
    -0.64
    scroll
    -0.63
     Xuan
    -0.61
    ulet
    -0.61
    stroke
    -0.60
    iary
    -0.60
    ghai
    -0.60
    POSITIVE LOGITS
    IUM
    1.32
    ITE
    1.22
    WARE
    1.19
    FORM
    1.17
    WORK
    1.13
    PASS
    1.12
    ANCE
    1.10
    EN
    1.09
    ET
    1.09
    DATA
    1.09
    Activations Density 0.150%

    No Known Activations