© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 7030
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic concepts, particularly those involving free markets and trade

    oai_token-act-pair · gpt-3.5-turbo

    references to concepts of free agency and market dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulhu
    -0.81
    ynski
    -0.73
     Nieto
    -0.70
     Lumpur
    -0.70
     Birch
    -0.69
     Archdemon
    -0.68
     Rath
    -0.68
     Bog
    -0.68
     Miko
    -0.68
     Uz
    -0.64
    POSITIVE LOGITS
    expression
    1.15
    throw
    1.04
    flo
    1.02
    serving
    1.02
    carry
    1.01
    charge
    0.96
    space
    0.96
    float
    0.95
    thinking
    0.95
    speech
    0.95
    Activations Density 0.042%

    No Known Activations