© 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. 1-RES-JB
    11. 14467
    Prev
    Next
    INDEX
    Explanations

    proper names or words related to people, likely politician or public figures

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their relationships or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.82
     Agents
    -0.74
    hold
    -0.74
    soDeliveryDate
    -0.72
     Cosponsors
    -0.72
    IAL
    -0.72
     message
    -0.69
    rab
    -0.67
    rants
    -0.67
    boards
    -0.65
    POSITIVE LOGITS
    oli
    1.41
    ague
    1.07
    olini
    0.98
    veyard
    0.93
    zzo
    0.92
    omon
    0.90
    oglu
    0.89
    ppo
    0.89
    uca
    0.88
    ola
    0.87
    Activations Density 0.005%

    No Known Activations