© 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. 6-RES-JB
    11. 17106
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Miss" followed by a title or first name

    oai_token-act-pair · gpt-3.5-turbo

    references to the title "Miss" followed by various names or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     brim
    -0.72
    Reviewed
    -0.69
    ©¶æ
    -0.68
    rd
    -0.67
    CAST
    -0.66
    OPLE
    -0.64
    OUGH
    -0.64
     Pwr
    -0.63
     bri
    -0.62
    chnology
    -0.61
    POSITIVE LOGITS
    ouri
    1.11
    hap
    0.94
    pelling
    0.94
    pelled
    0.91
    ippi
    0.85
    oria
    0.82
    pell
    0.81
    Miss
    0.79
    ipop
    0.79
    oul
    0.79
    Activations Density 0.017%

    No Known Activations