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

    Neuronpedia

    APICircuit 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. 0-RES-JB
    6. 4396
    Prev
    Next
    INDEX
    Explanations

    expressions related to satisfaction

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to satisfaction and dissatisfaction

    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
    orb
    -0.75
    icon
    -0.75
    phan
    -0.69
    opa
    -0.65
    Spread
    -0.65
    Draft
    -0.64
     loosely
    -0.63
     extensively
    -0.63
     banned
    -0.62
    eder
    -0.62
    POSITIVE LOGITS
     satisfaction
    4.09
     Satisf
    2.38
    atisf
    1.95
     dissatisfaction
    1.92
     gratification
    1.92
     enjoyment
    1.75
     satisfied
    1.71
     pleasure
    1.63
     fulfillment
    1.54
     satisfying
    1.46
    Activations Density 0.011%

    No Known Activations