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. 22831
    Prev
    Next
    INDEX
    Explanations

    terms related to meteorology and geological surveys

    oai_token-act-pair · gpt-3.5-turbo

    references to meteorological organizations and their data

    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
    TPP
    -0.77
    Interstitial
    -0.77
    twitch
    -0.73
    actionDate
    -0.73
    ardless
    -0.72
    nered
    -0.68
    advertising
    -0.68
    edited
    -0.65
    ivas
    -0.64
    TOR
    -0.64
    POSITIVE LOGITS
     forecast
    1.00
    ignty
    0.99
     forecasts
    0.91
     forecasting
    0.90
     advis
    0.86
     Satellite
    0.85
     Fisheries
    0.84
     glac
    0.81
     mathemat
    0.80
    ulty
    0.80
    Activations Density 0.081%

    No Known Activations