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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 10-RES-JB
    6. 4091
    Prev
    Next
    INDEX
    Explanations

    words related to strong positive emotions like joy, delight, and pleasure

    oai_token-act-pair · gpt-3.5-turbo

    expressions and references to joy and pleasure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 10 - joy

    No Comments

    Negative Logits
     Bans
    -0.68
     Canary
    -0.65
     braces
    -0.64
    heed
    -0.61
    pta
    -0.60
    pat
    -0.60
     adamant
    -0.60
     strict
    -0.59
    inx
    -0.58
    arin
    -0.58
    POSITIVE LOGITS
    ride
    1.22
    ously
    1.11
    fully
    1.10
    ous
    1.08
    sticks
    1.02
    urable
    0.97
    iously
    0.93
    joy
    0.92
    fulness
    0.88
    urous
    0.88
    Activations Density 0.091%

    No Known Activations