© 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. 14468
    Prev
    Next
    INDEX
    Explanations

    positive characteristics and values, such as reliability, friendship, curiosity, justice, and creativity

    oai_token-act-pair · gpt-3.5-turbo

    themes related to tolerance and social justice

    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
    cko
    -0.70
    herent
    -0.69
    assed
    -0.69
    upiter
    -0.69
    kees
    -0.67
    riber
    -0.66
    riad
    -0.66
    utor
    -0.65
    thal
    -0.65
    tale
    -0.65
    POSITIVE LOGITS
     albeit
    1.03
     etc
    0.85
     infiltration
    0.83
     which
    0.82
     whereby
    0.81
     aka
    0.80
     creativity
    0.78
    tein
    0.76
     whereas
    0.75
     namely
    0.75
    Activations Density 0.493%

    No Known Activations