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. 5-RES-JB
    6. 23932
    Prev
    Next
    INDEX
    Explanations

    natural disaster names, particularly hurricanes, which are likely to impact a region

    oai_token-act-pair · gpt-3.5-turbo

    references to significant hurricanes and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onym
    -0.81
    UGC
    -0.79
    cised
    -0.74
    Reviewer
    -0.71
    CHQ
    -0.71
    tainment
    -0.69
    onyms
    -0.67
    ellectual
    -0.66
    abase
    -0.65
    UP
    -0.65
    POSITIVE LOGITS
     besie
    0.80
     ravaged
    0.78
     landfall
    0.77
     devastated
    0.75
     struck
    0.75
     roared
    0.73
     wre
    0.71
    enburg
    0.70
     devast
    0.70
     evac
    0.69
    Activations Density 0.051%

    No Known Activations