© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9-RES-JB
    11. 23988
    Prev
    Next
    INDEX
    Explanations

    phrases related to cooperation and consequences

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to cooperation and consequences in societal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unveiling
    -0.80
    Born
    -0.78
     commemorate
    -0.78
     accomplishments
    -0.77
     debut
    -0.76
     inaugural
    -0.75
     acclaim
    -0.75
     unveiled
    -0.74
     celebrating
    -0.74
     marches
    -0.72
    POSITIVE LOGITS
    Solution
    1.11
     Solution
    1.07
    Example
    1.07
     Example
    1.01
     Suppose
    0.98
     fallacy
    0.95
     logic
    0.94
     workaround
    0.91
     scenario
    0.89
     loophole
    0.89
    Activations Density 1.159%

    No Known Activations