© 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. 10-RES-JB
    11. 18934
    Prev
    Next
    INDEX
    Explanations

    first person singular pronouns 'I' followed by various verbs and expressions

    oai_token-act-pair · gpt-3.5-turbo

    instances of self-reference or expressions of personal experience

    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
    senal
    -0.71
    cribed
    -0.68
    è¦ļéĨĴ
    -0.67
    ommel
    -0.67
    naire
    -0.66
    ablished
    -0.64
    oras
    -0.64
    urated
    -0.63
    esc
    -0.61
    ãĥ¼ãĥĨ
    -0.60
    POSITIVE LOGITS
     nonetheless
    1.35
     nevertheless
    1.29
     ALSO
    1.16
     also
    1.15
     dig
    1.05
     gotta
    1.04
     still
    1.02
     ain
    1.02
    etheless
    1.00
     beware
    0.98
    Activations Density 0.222%

    No Known Activations