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. 6750
    Prev
    Next
    INDEX
    Explanations

    words related to equipment or machinery

    oai_token-act-pair · gpt-3.5-turbo

    references to equipment 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
    lit
    -0.71
    nee
    -0.71
    ectar
    -0.70
    mary
    -0.68
    hua
    -0.67
    noon
    -0.67
    ¥
    -0.67
    uel
    -0.66
    heit
    -0.65
    athan
    -0.65
    POSITIVE LOGITS
     manufacturer
    0.96
     malf
    0.93
     equipment
    0.92
     manufacturers
    0.90
     malfunction
    0.85
     equip
    0.78
    paio
    0.73
     upgrades
    0.73
     manuals
    0.73
     supplier
    0.72
    Activations Density 0.034%

    No Known Activations