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. 16241
    Prev
    Next
    INDEX
    Explanations

    phrases related to maintaining or preserving something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "keep," focusing on its various contexts and usages

    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
    Interstitial
    -0.70
    NESS
    -0.66
    DragonMagazine
    -0.65
    acus
    -0.61
    ointed
    -0.61
    inges
    -0.61
    女
    -0.61
    odied
    -0.60
     GOODMAN
    -0.59
    NetMessage
    -0.59
    POSITIVE LOGITS
     tabs
    0.99
     pace
    0.93
     afloat
    0.89
     track
    0.88
     secrets
    0.78
     vigil
    0.78
     alive
    0.75
    overs
    0.73
    atural
    0.72
     quiet
    0.69
    Activations Density 0.038%

    No Known Activations