© 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. 11-RES-JB
    11. 20448
    Prev
    Next
    INDEX
    Explanations

    instances of the word "more" followed by other relevant words

    oai_token-act-pair · gpt-3.5-turbo

    references to increasing quantities or frequencies of occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    minus
    -0.67
    bat
    -0.67
    ixir
    -0.65
    atan
    -0.65
    pper
    -0.65
    hap
    -0.64
    xtap
    -0.64
    uca
    -0.64
    advertising
    -0.63
    emet
    -0.62
    POSITIVE LOGITS
     than
    1.08
     importantly
    1.07
     people
    1.06
     Americans
    0.91
     stringent
    0.89
     sophisticated
    0.87
     affluent
    0.85
     Australians
    0.84
     Canadians
    0.83
     emphasis
    0.83
    Activations Density 0.097%

    No Known Activations