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

    Neuronpedia

    APICircuit 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. 18238
    Prev
    Next
    INDEX
    Explanations

    mentions of flooding and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to floods and their impact on vulnerable regions

    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
    ccording
    -0.80
    cius
    -0.76
    ooth
    -0.72
    Ģ
    -0.71
    ACP
    -0.69
    CRIPTION
    -0.69
    nesota
    -0.66
     Lifetime
    -0.65
    doms
    -0.65
     livest
    -0.64
    POSITIVE LOGITS
    waters
    1.19
    plain
    1.03
     Katrina
    0.93
    water
    0.90
     Flood
    0.88
    lights
    0.87
     waters
    0.86
    lighting
    0.86
    proof
    0.86
    ãĤ¼
    0.86
    Activations Density 0.047%

    No Known Activations