Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 20087
    Prev
    Next
    INDEX
    Explanations

    words related to mental and emotional well-being and physical health

    oai_token-act-pair · gpt-3.5-turbo

    associations between sexual behavior and indicators of well-being or mental health

    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
    uitous
    -0.79
    Origin
    -0.77
    ranch
    -0.76
    odon
    -0.74
    Args
    -0.73
    selage
    -0.70
    agues
    -0.70
    ozo
    -0.69
     Canaver
    -0.69
    ulhu
    -0.69
    POSITIVE LOGITS
     satisfaction
    1.45
     happiness
    1.22
     enjoyment
    1.20
     wellbeing
    1.17
    esteem
    1.13
     attitudes
    1.10
     IQ
    1.10
     productivity
    1.10
     cognition
    1.09
     perceptions
    1.09
    Activations Density 0.298%

    No Known Activations