© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15704
    Prev
    Next
    INDEX
    Explanations

    terms related to various techniques and processes, possibly including medical procedures and technological methods

    oai_token-act-pair · gpt-3.5-turbo

    scientific and technical terms related to processes and techniques

    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
     Baz
    -0.80
    zl
    -0.76
    BuyableInstoreAndOnline
    -0.74
    ãĥĥãĥī
    -0.72
     Urug
    -0.71
    abase
    -0.69
    Pos
    -0.69
     Kham
    -0.67
    reon
    -0.63
     iT
    -0.63
    POSITIVE LOGITS
     techniques
    1.20
     whereby
    1.00
     tactics
    0.96
     technique
    0.96
     therapy
    0.96
     mechanisms
    0.95
     inhibitors
    0.94
     schemes
    0.93
     syndrome
    0.91
    utics
    0.91
    Activations Density 0.348%

    No Known Activations