© 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. 1-RES-JB
    11. 20348
    Prev
    Next
    INDEX
    Explanations

    negative words related to behavior or attitudes such as insanity, ignorance, arrogance, and hypocrisy

    oai_token-act-pair · gpt-3.5-turbo

    themes related to mental health issues and societal ignorance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amins
    -0.86
    icles
    -0.82
    icle
    -0.81
    Interstitial
    -0.80
    ergy
    -0.75
    ramer
    -0.73
    ta
    -0.73
    umm
    -0.73
    char
    -0.71
    arers
    -0.71
    POSITIVE LOGITS
     prejudice
    1.03
     intolerance
    0.91
    lessness
    0.89
    yip
    0.88
    xtap
    0.88
    fulness
    0.87
     stupidity
    0.84
     ignorance
    0.84
     malice
    0.82
    ophobia
    0.80
    Activations Density 0.051%

    No Known Activations