© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-JB
    11. 10518
    Prev
    Next
    INDEX
    Explanations

    phrases related to various organizations, initiatives, and actions

    oai_token-act-pair · gpt-3.5-turbo

    action verbs related to social initiatives and movements

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

    No Comments

    Negative Logits
     discharge
    -0.74
     silence
    -0.72
     exha
    -0.70
     externalToEVAOnly
    -0.69
    istration
    -0.67
    antically
    -0.67
    etheless
    -0.66
     unnecess
    -0.66
     occas
    -0.65
     tom
    -0.65
    POSITIVE LOGITS
    ings
    1.02
    Maker
    0.93
    away
    0.92
    ers
    0.86
    aways
    0.83
    ables
    0.83
    Point
    0.82
    zon
    0.81
     Assist
    0.81
    ership
    0.80
    Activations Density 0.191%

    No Known Activations