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. 2-RES-JB
    6. 3709
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases related to meeting a need or desire

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "satisfy" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mehran
    -0.68
     Bucc
    -0.64
     Caller
    -0.64
     Sachs
    -0.63
    sych
    -0.62
     Banner
    -0.61
    glas
    -0.61
    olan
    -0.60
    alion
    -0.60
    Downloadha
    -0.59
    POSITIVE LOGITS
     satisfy
    0.90
    meat
    0.85
     tastes
    0.83
    )=(
    0.80
     appease
    0.78
    ppings
    0.76
    VILLE
    0.75
    vey
    0.74
    strings
    0.74
     appet
    0.74
    Activations Density 0.026%

    No Known Activations