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. 21424
    Prev
    Next
    INDEX
    Explanations

    phrases related to the Federal Aviation Administration (FAA)

    oai_token-act-pair · gpt-3.5-turbo

    references to the FAA (Federal Aviation Administration) and its related activities

    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
    chnology
    -0.74
    ODUCT
    -0.67
     whale
    -0.66
    oice
    -0.65
    atown
    -0.65
    OPLE
    -0.61
     Burnett
    -0.60
     boundaries
    -0.60
     starch
    -0.60
     Borders
    -0.60
    POSITIVE LOGITS
    ras
    0.96
    rely
    0.92
    rals
    0.85
    ris
    0.84
     Seym
    0.83
    req
    0.83
    eki
    0.82
    rik
    0.82
    HT
    0.80
    rack
    0.79
    Activations Density 0.035%

    No Known Activations