© 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. 2-RES-JB
    11. 14196
    Prev
    Next
    INDEX
    Explanations

    instances where action is proposed or emphasized

    oai_token-act-pair · gpt-3.5-turbo

    the word "make" and its various forms relating to causation or creation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.66
    bour
    -0.64
     Vest
    -0.63
    ---------
    -0.63
     Leban
    -0.62
    ORPG
    -0.61
     nurs
    -0.61
     Fenrir
    -0.61
     Pengu
    -0.58
     Ples
    -0.57
    POSITIVE LOGITS
    hift
    1.00
     sure
    0.98
    awaru
    0.87
    ailable
    0.86
    ÄŁ
    0.80
    elling
    0.80
    itions
    0.79
    escape
    0.77
    emort
    0.76
    urate
    0.75
    Activations Density 0.148%

    No Known Activations