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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 21736
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific geographical locations or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to the Standing Rock movement or protests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }{
    -0.74
     marketers
    -0.69
     sens
    -0.66
     glean
    -0.62
     mail
    -0.60
     funnel
    -0.60
    omas
    -0.58
     gadget
    -0.58
     alarm
    -0.57
     numer
    -0.57
    POSITIVE LOGITS
     Standing
    4.32
    Standing
    2.35
     Sitting
    1.69
     standing
    1.26
     Lak
    1.16
     STAND
    1.07
     Falling
    1.05
     Stand
    1.05
     Idle
    1.02
     kneeling
    1.00
    Activations Density 0.013%

    No Known Activations