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. 7-RES-JB
    6. 4272
    Prev
    Next
    INDEX
    Explanations

    expressions related to feeling tired or fed up with something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of fatigue or weariness related to recurring situations or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LAN
    -0.71
    isite
    -0.70
    rha
    -0.70
    pedia
    -0.69
    osity
    -0.67
    MIT
    -0.66
    nostic
    -0.65
    UA
    -0.65
    afort
    -0.65
    ourage
    -0.64
    POSITIVE LOGITS
     seeing
    0.93
     wasting
    0.86
     waiting
    0.77
     humiliation
    0.77
     banging
    0.76
     battling
    0.75
     tink
    0.73
     hearing
    0.73
     boring
    0.72
     complaining
    0.71
    Activations Density 0.060%

    No Known Activations