© 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. 10-RES-JB
    11. 12845
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and finance

    oai_token-act-pair · gpt-3.5-turbo

    connections or associations involving the word "and."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤĵ
    -0.82
    Laughs
    -0.67
    burgh
    -0.67
    wives
    -0.66
    poons
    -0.65
    dden
    -0.65
    hiba
    -0.65
    atten
    -0.64
    ei
    -0.64
    atts
    -0.64
    POSITIVE LOGITS
     related
    1.04
     its
    1.01
     entrepreneurship
    1.00
     globalization
    0.97
     sustainability
    0.95
     sexuality
    0.94
     automation
    0.94
     extremism
    0.93
     spirituality
    0.93
     how
    0.91
    Activations Density 0.269%

    No Known Activations