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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 0-RES-JB
    6. 5513
    Prev
    Next
    INDEX
    Explanations

    words related to vitamins

    oai_token-act-pair · gpt-3.5-turbo

    references to vitamins and dietary trusts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mel
    -0.86
    natureconservancy
    -0.78
    redd
    -0.74
    clus
    -0.74
    tsky
    -0.71
    bug
    -0.70
    inventoryQuantity
    -0.68
    ses
    -0.68
    Charg
    -0.68
    etsk
    -0.67
    POSITIVE LOGITS
    ã쮿
    0.68
    urdue
    0.66
    ãĥĺ
    0.66
    isan
    0.64
     Ops
    0.62
     skilled
    0.62
    ombo
    0.61
    zai
    0.60
    iah
    0.60
    owan
    0.59
    Activations Density 0.001%

    No Known Activations