© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 22371
    Prev
    Next
    INDEX
    Explanations

    references to transportation facilities or modes, especially related to trains and freight

    oai_token-act-pair · gpt-3.5-turbo

    terms related to transportation systems, specifically trains and railroads

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hague
    -0.77
    berra
    -0.77
     Holder
    -0.75
     Julian
    -0.72
     Ambrose
    -0.70
     presumptive
    -0.67
    ados
    -0.65
    untu
    -0.64
     Ec
    -0.63
    oret
    -0.63
    POSITIVE LOGITS
     trains
    1.19
     Amtrak
    1.15
    roads
    1.12
     locom
    1.10
     Railroad
    1.02
     railways
    1.01
     railroad
    1.00
    Train
    0.98
    tracks
    0.98
    Rail
    0.96
    Activations Density 0.021%

    No Known Activations