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. 8-RES-JB
    6. 6703
    Prev
    Next
    INDEX
    Explanations

    commands or instructions to perform an action on the internet, such as finding information or resources

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Find" along with related phrases and calls to action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    perty
    -0.69
    piring
    -0.67
    WARNING
    -0.67
    icum
    -0.67
     concess
    -0.67
     fracturing
    -0.66
    bara
    -0.66
     indign
    -0.65
     horm
    -0.64
     tremend
    -0.62
    POSITIVE LOGITS
    ings
    1.06
    ById
    0.94
    lay
    0.81
    ers
    0.75
    ations
    0.74
    find
    0.73
    ational
    0.73
    INGS
    0.73
    imon
    0.73
    ãĤ¤ãĥĪ
    0.71
    Activations Density 0.046%

    No Known Activations