© 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. 2922
    Prev
    Next
    INDEX
    Explanations

    terms related to controversial or challenging topics, often involving legal or ethical considerations

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "issue of" indicating discussions surrounding various contentious topics

    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
    iaries
    -0.79
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.76
    rites
    -0.71
    ername
    -0.69
    uries
    -0.68
    Catalog
    -0.65
    iously
    -0.65
    gian
    -0.64
    âĹ¼
    -0.64
    ksh
    -0.63
    POSITIVE LOGITS
     whether
    1.02
     legality
    0.84
     JUSTICE
    0.84
     fairness
    0.83
    whether
    0.73
     course
    0.72
     why
    0.72
     homosexuality
    0.71
     how
    0.68
     combating
    0.68
    Activations Density 0.091%

    No Known Activations