© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 11302
    Prev
    Next
    INDEX
    Explanations

    words related to roads and road-related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to "road" in various contexts

    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
     pant
    -0.68
     embell
    -0.64
     invoked
    -0.62
     lav
    -0.62
     values
    -0.60
     cast
    -0.60
     000000
    -0.59
     jan
    -0.58
     invent
    -0.58
     wit
    -0.56
    POSITIVE LOGITS
    road
    4.67
    roads
    2.14
    Road
    2.06
     road
    1.56
     Roads
    1.49
     Road
    1.41
     roads
    1.33
    street
    1.12
     roadway
    1.06
    rog
    1.01
    Activations Density 0.010%

    No Known Activations