© 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. 9-RES-JB
    11. 20845
    Prev
    Next
    INDEX
    Explanations

    terms related to initializing, starting, or setting up processes

    oai_token-act-pair · gpt-3.5-turbo

    references to initialization and system startup processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uay
    -0.73
    berman
    -0.72
    epad
    -0.63
     bearer
    -0.62
    ãĥĥãĥī
    -0.61
    ography
    -0.60
    aph
    -0.60
    ographies
    -0.59
    alez
    -0.59
    inates
    -0.59
    POSITIVE LOGITS
    tenance
    0.97
    itial
    0.82
    ALLY
    0.77
    strap
    0.74
    iation
    0.71
    TIME
    0.70
    ally
    0.69
    ting
    0.68
    othal
    0.67
    bell
    0.66
    Activations Density 0.144%

    No Known Activations