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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8-RES-JB
    6. 5846
    Prev
    Next
    INDEX
    Explanations

    words related to disasters or accidents

    oai_token-act-pair · gpt-3.5-turbo

    references to destruction and disaster

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VIDIA
    -0.75
    specific
    -0.73
    TPP
    -0.72
    centric
    -0.70
    CLASSIFIED
    -0.70
    phasis
    -0.70
    ĸļ
    -0.69
    encers
    -0.68
    ãĤ¦ãĤ¹
    -0.68
    classes
    -0.68
    POSITIVE LOGITS
     wreckage
    0.97
     Fukushima
    0.97
     debris
    0.86
     excavation
    0.83
     aftermath
    0.83
     roadside
    0.82
     evacuated
    0.79
     MH
    0.77
     Sochi
    0.77
     crater
    0.76
    Activations Density 0.588%

    No Known Activations