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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 14799
    Prev
    Next
    INDEX
    Explanations

    words related to traffic congestion or physical congestion

    oai_token-act-pair · gpt-3.5-turbo

    terms related to traffic and crowding issues

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

    No Comments

    Negative Logits
    sonian
    -0.98
    tell
    -0.83
     Eisen
    -0.74
    arian
    -0.68
    ta
    -0.67
    hetical
    -0.65
    OGR
    -0.63
    ochet
    -0.63
    thing
    -0.63
    ining
    -0.63
    POSITIVE LOGITS
     congestion
    1.19
     freeway
    0.94
     congest
    0.91
     queue
    0.78
     jams
    0.77
     highways
    0.75
     queues
    0.73
    wagon
    0.72
     worsened
    0.72
    capacity
    0.71
    Activations Density 0.011%

    No Known Activations