© 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. 7655
    Prev
    Next
    INDEX
    Explanations

    words related to personal values, integrity, and emotional expression

    oai_token-act-pair · gpt-3.5-turbo

    statements related to control, power, and influence

    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
    ģĸ
    -0.87
    »Ĵ
    -0.83
    geons
    -0.69
    ãĥīãĥ©
    -0.69
    emed
    -0.69
    iatus
    -0.67
    ulla
    -0.67
    iatrics
    -0.65
    odon
    -0.65
    quished
    -0.63
    POSITIVE LOGITS
     creativity
    1.25
     honesty
    1.20
     bravery
    1.18
     sophistication
    1.18
     generosity
    1.18
     ingenuity
    1.14
     elegance
    1.13
     decency
    1.12
     professionalism
    1.11
     humility
    1.09
    Activations Density 0.249%

    No Known Activations