© 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. 10-RES-JB
    11. 20597
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or tasks that involve others

    oai_token-act-pair · gpt-3.5-turbo

    action words related to hosting, passing legislation, and addressing various social issues

    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
     wrestlers
    -0.61
     mayors
    -0.59
    metics
    -0.54
     startups
    -0.53
    devices
    -0.53
     dstg
    -0.53
     girls
    -0.52
     colleges
    -0.52
     cures
    -0.52
     Malays
    -0.52
    POSITIVE LOGITS
     this
    1.02
     the
    0.87
    this
    0.86
     it
    0.73
    the
    0.72
     such
    0.67
    itled
    0.65
     THIS
    0.64
     another
    0.63
     an
    0.62
    Activations Density 0.787%

    No Known Activations