© 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. 11251
    Prev
    Next
    INDEX
    Explanations

    call-to-action phrases like 'Like' or 'Check'

    oai_token-act-pair · gpt-3.5-turbo

    the social media engagement metrics related to the word "Like."

    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
    tein
    -0.85
    inas
    -0.74
    rete
    -0.72
    deal
    -0.71
    ennes
    -0.71
    endiary
    -0.70
    restrial
    -0.69
    ilic
    -0.69
    inez
    -0.68
    lehem
    -0.68
    POSITIVE LOGITS
    lihood
    1.89
    liest
    0.82
     Mothers
    0.75
    minded
    0.74
    liness
    0.74
    lier
    0.74
     minded
    0.71
     Likes
    0.67
    ability
    0.67
     Submit
    0.66
    Activations Density 0.050%

    No Known Activations