© 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. 0-RES-JB
    11. 15613
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms related to healthcare or government organizations

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the "HC" acronym, likely indicating formal organizations or classifications

    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
     bark
    -0.69
     Redmond
    -0.67
     Boris
    -0.67
     Pepe
    -0.67
     springs
    -0.65
     Yas
    -0.65
     Ariel
    -0.64
     Vid
    -0.64
     apples
    -0.64
     oper
    -0.64
    POSITIVE LOGITS
    HC
    4.50
     HC
    2.16
    HL
    1.52
    HS
    1.52
    HP
    1.43
    HH
    1.41
    HB
    1.33
    JC
    1.32
    MC
    1.26
    TC
    1.26
    Activations Density 0.011%

    No Known Activations