© 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. 7-RES-JB
    11. 1637
    Prev
    Next
    INDEX
    Explanations

    superlatives describing things as the best or the greatest

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating comparisons of quality or ranking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onto
    -0.76
    gow
    -0.76
    heit
    -0.76
    matter
    -0.74
    otto
    -0.71
    brance
    -0.70
    aker
    -0.69
    livion
    -0.67
    rium
    -0.66
    undle
    -0.66
    POSITIVE LOGITS
     pillars
    0.94
     professions
    0.89
     distingu
    0.86
     inventions
    0.86
     inspir
    0.86
     ways
    0.82
     recurring
    0.80
     examples
    0.79
     manifestations
    0.78
     avenues
    0.77
    Activations Density 0.119%

    No Known Activations