© 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. 7066
    Prev
    Next
    INDEX
    Explanations

    words related to abrupt movement or change

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the letter combination "j" followed by the digit "2"

    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
     adjourn
    -0.63
     Fargo
    -0.62
     Calder
    -0.60
     Illum
    -0.59
    doors
    -0.59
     Dull
    -0.59
     Creed
    -0.58
     DeVos
    -0.58
     tanks
    -0.57
     Hendricks
    -0.57
    POSITIVE LOGITS
    igsaw
    1.40
    umbo
    1.32
    okingly
    1.30
    ockey
    1.30
    okers
    1.21
    agged
    1.19
    ingle
    1.16
    aund
    1.16
    inx
    1.15
    ogging
    1.14
    Activations Density 0.026%

    No Known Activations