© 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. 23859
    Prev
    Next
    INDEX
    Explanations

    instances where someone publicly criticizes or points out something or someone

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing calling someone out or criticizing actions

    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
     gamble
    -0.67
     princip
    -0.66
    fing
    -0.63
    oreal
    -0.62
    entry
    -0.61
     mint
    -0.61
     assum
    -0.59
    parable
    -0.59
     confir
    -0.58
    ushima
    -0.58
    POSITIVE LOGITS
    stretched
    0.98
     loud
    0.97
    casts
    0.82
     loudly
    0.74
    posts
    0.74
     Sinclair
    0.72
    tical
    0.70
    lier
    0.70
    tics
    0.70
    smart
    0.69
    Activations Density 0.018%

    No Known Activations