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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 2366
    Prev
    Next
    INDEX
    Explanations

    the word "work"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "work" in various contexts

    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
    antha
    -0.76
    ylon
    -0.71
     Ukrain
    -0.68
    anamo
    -0.66
     Bubble
    -0.66
     Augustus
    -0.65
    netflix
    -0.63
    osate
    -0.61
    iren
    -0.61
     Flavoring
    -0.61
    POSITIVE LOGITS
     tirelessly
    1.18
     diligently
    1.10
     collabor
    1.10
    bench
    1.09
     ethic
    1.01
    hops
    0.98
    heet
    0.94
    flows
    0.90
     toward
    0.90
     harder
    0.88
    Activations Density 0.082%

    No Known Activations