© 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. 0-RES-JB
    11. 13422
    Prev
    Next
    INDEX
    Explanations

    files related to specific functions or actions performed on files within a system

    oai_token-act-pair · gpt-3.5-turbo

    references to markdown (md) formats and text file (txt) indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kinnikuman
    -0.69
     fitting
    -0.67
     repertoire
    -0.64
     stabil
    -0.63
     paradox
    -0.63
     Fairy
    -0.63
     recruitment
    -0.63
     mobil
    -0.62
    Mach
    -0.62
     Tot
    -0.61
    POSITIVE LOGITS
    md
    4.19
    txt
    1.95
     md
    1.48
    json
    1.47
    mt
    1.27
    vm
    1.22
    ml
    1.20
    td
    1.20
    mc
    1.17
    tx
    1.17
    Activations Density 0.007%

    No Known Activations