© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 20520
    Prev
    Next
    INDEX
    Explanations

    fears or concerns related to potential negative consequences or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing concerns about potential negative outcomes or threats

    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
    •layer 6 - fear

    No Comments

    Negative Logits
    noon
    -0.76
     Walton
    -0.66
     Clara
    -0.65
    OTUS
    -0.64
    IES
    -0.63
    ":{"
    -0.63
    mentioned
    -0.62
    daq
    -0.62
    cember
    -0.62
    Quotes
    -0.62
    POSITIVE LOGITS
     unfairly
    0.96
     inappropriately
    0.79
     improperly
    0.78
     underestimated
    0.78
     misunderstood
    0.77
     embold
    0.75
     jeopard
    0.75
     influenced
    0.74
     inadequ
    0.73
     mishand
    0.73
    Activations Density 0.474%

    No Known Activations