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. 3-RES-JB
    6. 14573
    Prev
    Next
    INDEX
    Explanations

    items or objects that can be stored or carried in a pocket

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of a pocket

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ANGEL
    -0.88
    =-=-=-=-
    -0.74
    IAS
    -0.73
    ————————————————
    -0.72
    rd
    -0.72
     Cosponsors
    -0.67
    Posted
    -0.65
    */(
    -0.65
    Reviewer
    -0.64
    ETF
    -0.63
    POSITIVE LOGITS
    pocket
    0.99
     pocket
    0.95
    knife
    0.95
    wallet
    0.87
     Pocket
    0.84
    ably
    0.84
    book
    0.84
    books
    0.84
    bler
    0.83
    clip
    0.80
    Activations Density 0.008%

    No Known Activations