© 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. 0-RES-JB
    11. 13558
    Prev
    Next
    INDEX
    Explanations

    phrases related to the name "Sergey Pisin"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual or character associated with the name "Psy."

    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
     compuls
    -0.65
     sparing
    -0.61
     backers
    -0.60
     discretion
    -0.59
     Beacon
    -0.59
     hearts
    -0.58
     timelines
    -0.58
     warrants
    -0.56
     rehabilitation
    -0.56
     swings
    -0.56
    POSITIVE LOGITS
    si
    4.75
    sis
    1.67
    sie
    1.58
    SI
    1.55
    sa
    1.52
    sin
    1.50
    ti
    1.30
    ses
    1.29
    sg
    1.25
    di
    1.24
    Activations Density 0.010%

    No Known Activations