© 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. 5930
    Prev
    Next
    INDEX
    Explanations

    strongly negative or cautionary words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    words related to advertisements

    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
     shorth
    -0.79
     Jenner
    -0.71
    AH
    -0.70
     Lauder
    -0.70
     stret
    -0.69
     Kot
    -0.68
    è¦ļéĨĴ
    -0.67
     Shack
    -0.65
     KR
    -0.65
     Winc
    -0.65
    POSITIVE LOGITS
    ception
    1.28
    vance
    1.21
    mitted
    1.19
    mission
    1.17
    istant
    1.14
    ceptive
    1.10
    vasive
    1.08
    apter
    1.08
    venture
    1.07
    vice
    1.06
    Activations Density 0.072%

    No Known Activations