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. 6-RES-JB
    6. 11275
    Prev
    Next
    INDEX
    Explanations

    the word "zero" or phrases related to the concept of zero

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "zero" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.90
    Interstitial
    -0.81
    akov
    -0.75
    areth
    -0.74
    lov
    -0.74
    soDeliveryDate
    -0.73
    regor
    -0.73
    icken
    -0.72
    rough
    -0.71
    ammad
    -0.70
    POSITIVE LOGITS
     Hedge
    0.87
     tolerance
    0.81
     percent
    0.79
     zero
    0.77
    zero
    0.77
    een
    0.77
     Escape
    0.76
    ishly
    0.75
    hole
    0.75
     amount
    0.74
    Activations Density 0.022%

    No Known Activations