© 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. 1-RES-JB
    11. 14235
    Prev
    Next
    INDEX
    Explanations

    adjectives describing something as complete or thorough

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating completeness or totality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.90
     Disciple
    -0.83
    achu
    -0.73
     Pike
    -0.71
    */(
    -0.70
     Cause
    -0.69
    aminer
    -0.68
    Reviewer
    -0.67
    gee
    -0.67
    ackle
    -0.65
    POSITIVE LOGITS
     qualified
    0.93
     fled
    0.87
     clothed
    0.86
     exting
    0.83
     immersed
    0.82
     transitioned
    0.81
    rehensive
    0.80
    qualified
    0.80
     adequate
    0.79
     equipped
    0.78
    Activations Density 0.009%

    No Known Activations