© 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. 3-RES-JB
    11. 15970
    Prev
    Next
    INDEX
    Explanations

    phrases related to opportunities or chances

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating opportunities or chances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Balt
    -0.83
    bane
    -0.79
    UFF
    -0.77
    SourceFile
    -0.77
    minus
    -0.75
    furt
    -0.73
    Introduced
    -0.71
    Wan
    -0.71
    Mu
    -0.71
    bush
    -0.70
    POSITIVE LOGITS
     indulge
    0.78
     redemption
    0.77
     commute
    0.75
     snag
    0.74
     glimpse
    0.74
     optimism
    0.72
    awaru
    0.71
     escape
    0.71
     peek
    0.71
     solve
    0.69
    Activations Density 0.221%

    No Known Activations