© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 11289
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a potential outcome or benefit

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate potential outcomes or possibilities

    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
    mere
    -0.68
    quickShipAvailable
    -0.62
     Said
    -0.62
    reports
    -0.59
    CTV
    -0.59
    urance
    -0.59
    ready
    -0.58
     Tempest
    -0.57
    breaks
    -0.57
    lights
    -0.57
    POSITIVE LOGITS
     capitalize
    1.08
     reap
    0.99
     become
    0.97
     lose
    0.96
     explode
    0.96
     gain
    0.94
     inherit
    0.89
     benefit
    0.89
     receive
    0.88
     intensify
    0.88
    Activations Density 0.110%

    No Known Activations