Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 11505
    Prev
    Next
    INDEX
    Explanations

    proper names or phrases related to people or characters with a specific name 'Dario'

    oai_token-act-pair · gpt-3.5-turbo

    references to characters or roles in film or television

    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
    ivities
    -1.10
    urations
    -0.87
    urers
    -0.85
    uring
    -0.85
    ues
    -0.82
    endor
    -0.81
    uration
    -0.80
    iple
    -0.80
    erton
    -0.80
    iency
    -0.79
    POSITIVE LOGITS
    BuyableInstoreAndOnline
    0.78
     Typhoon
    0.74
    BILITY
    0.74
    cia
    0.73
     Bots
    0.71
    cles
    0.71
    xual
    0.70
    vernment
    0.70
    active
    0.69
    nces
    0.68
    Activations Density 0.031%

    No Known Activations