© 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 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. 3-RES-JB
    11. 5099
    Prev
    Next
    INDEX
    Explanations

    instances where an action is suggested or recommended

    oai_token-act-pair · gpt-3.5-turbo

    expressions of obligation or recommendations

    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
     Puzzle
    -0.67
    dream
    -0.66
    oric
    -0.65
    Arab
    -0.63
     Zone
    -0.63
     Kramer
    -0.61
    gren
    -0.60
    ZI
    -0.60
     Hou
    -0.60
    ula
    -0.59
    POSITIVE LOGITS
    DragonMagazine
    0.91
    ratulations
    0.82
    EStream
    0.81
     actionGroup
    0.80
    ĺħ
    0.80
     rightfully
    0.77
    ILY
    0.74
    igham
    0.73
     attent
    0.73
    entious
    0.73
    Activations Density 0.006%

    No Known Activations