© 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 EvalsExportsinterp-engineNEWAPI 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. 23480
    Prev
    Next
    INDEX
    Explanations

    phrases indicating emphasis or direction in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "didn't" in various forms or contexts

    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
     Palest
    -0.70
     Libyan
    -0.67
     Mous
    -0.64
     lodging
    -0.64
     RAD
    -0.63
     Drawn
    -0.61
    anwhile
    -0.61
     Mour
    -0.59
     Sapphire
    -0.58
     board
    -0.58
    POSITIVE LOGITS
    Į
    1.09
    ¬
    1.09
    ¢
    1.08
    ¡
    1.08
    ı
    1.06
    ł
    1.06
    į
    1.05
    ¿
    1.04
    ¹
    1.03
    Ĭ
    0.99
    Activations Density 0.232%

    No Known Activations