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. 5627
    Prev
    Next
    INDEX
    Explanations

    references to destruction and damage from disasters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to destruction and damage to buildings and infrastructure

    oai_token-act-pair · gpt-3.5-turbo
    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
    rogram
    -0.96
    antics
    -0.74
    onom
    -0.71
    cific
    -0.70
    imum
    -0.69
    ennial
    -0.67
    ypes
    -0.66
    irlfriend
    -0.65
    OGR
    -0.65
    owsky
    -0.65
    POSITIVE LOGITS
     evacuated
    0.96
     reopened
    0.95
     buildings
    0.90
     belonging
    0.88
    itals
    0.81
     nearby
    0.80
    myra
    0.76
     damaged
    0.76
     entrances
    0.76
     collapsed
    0.75
    Activations Density 0.559%

    No Known Activations