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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 13285
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Bit" with varying adjectives

    oai_token-act-pair · gpt-3.5-turbo

    references to Bitcoin or related cryptocurrencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ammad
    -0.75
     Grave
    -0.65
    ãĤĭ
    -0.62
     Pend
    -0.62
    inson
    -0.61
     arisen
    -0.61
     Cros
    -0.60
    theless
    -0.60
     Superior
    -0.60
     Siber
    -0.59
    POSITIVE LOGITS
    terness
    1.44
    umen
    1.23
    ches
    1.18
    coins
    1.14
    umin
    1.11
    buck
    1.10
    Torrent
    1.04
    maps
    1.04
    wig
    1.03
    map
    1.02
    Activations Density 0.029%

    No Known Activations