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. 1-RES-JB
    6. 17482
    Prev
    Next
    INDEX
    Explanations

    phrases related to the name "Cabin" or "Cabin Fever"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and their contributions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hurricanes
    -0.70
     Hobby
    -0.64
     Brittany
    -0.64
    Trend
    -0.61
     Expend
    -0.60
     Caucasian
    -0.59
     Savannah
    -0.59
     STAR
    -0.59
     Sight
    -0.58
     Daytona
    -0.58
    POSITIVE LOGITS
    abin
    1.35
    ieri
    1.03
    owitz
    1.01
    ogi
    1.00
    ement
    0.98
    urations
    0.88
    ove
    0.83
    abal
    0.82
    jamin
    0.82
    nect
    0.81
    Activations Density 0.005%

    No Known Activations