© 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. 3-RES-JB
    11. 16454
    Prev
    Next
    INDEX
    Explanations

    greetings or introductions

    oai_token-act-pair · gpt-3.5-turbo

    greetings and expressions of "hi"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    士
    -0.85
    */(
    -0.79
     Awakens
    -0.78
    )</
    -0.73
     Rebell
    -0.73
    arian
    -0.68
    ãĥ¯
    -0.65
     destro
    -0.65
    cru
    -0.61
     Prophe
    -0.61
    POSITIVE LOGITS
    yip
    0.93
    Hi
    0.87
    WARD
    0.83
    Fi
    0.81
    hey
    0.80
     Hi
    0.78
    roy
    0.75
    pped
    0.74
    bye
    0.73
    earch
    0.73
    Activations Density 0.008%

    No Known Activations