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. 0-RES-JB
    6. 21353
    Prev
    Next
    INDEX
    Explanations

    terms related to broadband technology and specific names such as "Wheeler"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Broadband" and related terms in the context of telecommunications

    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
    externalActionCode
    -0.90
    soDeliveryDate
    -0.75
    lore
    -0.72
    elo
    -0.72
    giving
    -0.66
    ador
    -0.66
    inventoryQuantity
    -0.65
    dal
    -0.64
    */(
    -0.64
    Swe
    -0.63
    POSITIVE LOGITS
     Broad
    2.58
    bps
    2.46
     Mbps
    1.45
    Mbps
    1.43
     broadband
    1.40
     Wheeler
    1.15
     Gupta
    1.06
     Cable
    0.99
     telecom
    0.96
     Fast
    0.91
    Activations Density 0.019%

    No Known Activations