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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-RES-JB
    6. 5750
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "work" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the word "work" and its variations in the context of artistic or creative endeavors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ukrain
    -0.99
    wcs
    -0.69
    Args
    -0.65
    angular
    -0.65
    ylon
    -0.63
     snap
    -0.62
     Gord
    -0.62
    iren
    -0.61
     champagne
    -0.60
     Missile
    -0.60
    POSITIVE LOGITS
     ethic
    1.39
    flows
    1.26
    station
    1.21
    aday
    1.07
    manship
    1.05
    bench
    1.05
    horse
    0.99
    mate
    0.90
    hops
    0.89
    mates
    0.88
    Activations Density 0.042%

    No Known Activations