© 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. 12-RES-JB
    11. 3484
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals performing specific actions or holding particular positions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    the verb "has" in various contexts related to possession or experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wake
    -0.86
    eem
    -0.85
     Awakens
    -0.80
    ļéĨĴ
    -0.80
    wrap
    -0.80
    uating
    -0.79
    roll
    -0.77
    imation
    -0.75
    onnaissance
    -0.75
    terday
    -0.75
    POSITIVE LOGITS
     overseen
    1.20
     authored
    1.19
     worked
    1.17
     been
    1.12
     served
    1.11
     collaborated
    1.07
     extensive
    1.06
     lived
    1.06
     championed
    1.05
     resided
    1.05
    Activations Density 0.188%

    No Known Activations