© 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. 0-RES-JB
    11. 13909
    Prev
    Next
    INDEX
    Explanations

    terms related to controversial topics or moral issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to controversial sexual orientations and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DEC
    -0.81
     HAL
    -0.70
     standard
    -0.69
     Chou
    -0.69
     Bench
    -0.69
     hash
    -0.68
     plain
    -0.67
    point
    -0.66
     point
    -0.66
     fore
    -0.66
    POSITIVE LOGITS
    ilia
    4.33
    ilic
    2.03
    ilian
    1.95
    ili
    1.86
    iles
    1.67
    ile
    1.43
    obia
    1.42
    ilial
    1.35
    iliary
    1.34
    ila
    1.29
    Activations Density 0.009%

    No Known Activations