© 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. 11-RES-JB
    11. 22448
    Prev
    Next
    INDEX
    Explanations

    names of people or entities, particularly with a focus on political figures and institutions

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals or groups associated with political or social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    er
    -1.03
    eros
    -0.97
    uras
    -0.92
    eric
    -0.87
    shire
    -0.87
    urus
    -0.86
    oise
    -0.84
    eur
    -0.82
    ersen
    -0.81
    uran
    -0.80
    POSITIVE LOGITS
    ãģĨ
    0.61
     à¨
    0.57
    å½
    0.56
    大
    0.55
    ãģ£
    0.54
     Ùħ
    0.52
    åį
    0.52
    èĥ
    0.51
    ÙĴ
    0.51
    ä¼
    0.51
    Activations Density 0.237%

    No Known Activations