© 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. 10-RES-JB
    11. 5433
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or instructions

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases that end with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deserved
    -0.80
     lately
    -0.78
     mysteriously
    -0.74
     adversity
    -0.74
     embarrass
    -0.73
     amazingly
    -0.73
    strate
    -0.73
    aciously
    -0.72
     assassinate
    -0.71
     passionately
    -0.70
    POSITIVE LOGITS
     Previously
    1.31
     Customers
    1.22
    Previously
    1.19
    Applic
    1.18
     Currently
    1.16
     Additionally
    1.15
     Users
    1.14
     Those
    1.14
     Alternatively
    1.09
     Applic
    1.07
    Activations Density 0.353%

    No Known Activations