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. 10-RES-JB
    6. 9573
    Prev
    Next
    INDEX
    Explanations

    references to traffic-related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of traffic-related topics and issues

    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
    sonian
    -1.17
    utical
    -0.83
    nai
    -0.78
    atever
    -0.78
    lain
    -0.77
    arity
    -0.77
    theless
    -0.74
     Lazarus
    -0.72
    krit
    -0.71
    thing
    -0.67
    POSITIVE LOGITS
     jams
    1.38
     congestion
    1.35
     cones
    1.02
     lanes
    1.02
     fatalities
    1.00
     calming
    0.99
     traffic
    0.99
     accidents
    0.97
     jam
    0.93
     flow
    0.93
    Activations Density 0.043%

    No Known Activations