© 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. 11426
    Prev
    Next
    INDEX
    Explanations

    words related to different types of ideologies or groups

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to specific minority groups

    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
    ntil
    -0.92
    lished
    -0.80
    ufact
    -0.75
    merce
    -0.74
    swer
    -0.72
    otiation
    -0.71
    direction
    -0.71
    perature
    -0.71
    acea
    -0.69
    rama
    -0.67
    POSITIVE LOGITS
    ites
    1.23
    ite
    1.13
    geist
    0.85
    ITE
    0.75
    chool
    0.75
    eer
    0.74
    hell
    0.70
    ilver
    0.69
    itic
    0.68
    ongs
    0.67
    Activations Density 0.009%

    No Known Activations