© 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. 2-RES-JB
    11. 9230
    Prev
    Next
    INDEX
    Explanations

    terms related to train derailments

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "derail" and its variations, indicating discussions around disruption or accidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ternity
    -0.72
     Kinnikuman
    -0.72
    anamo
    -0.69
    Reviewer
    -0.67
     Reach
    -0.67
    estate
    -0.66
    iping
    -0.66
    umption
    -0.64
    guyen
    -0.63
    archs
    -0.63
    POSITIVE LOGITS
     derail
    1.61
     derailed
    1.33
    ments
    0.85
     freight
    0.80
     Amtrak
    0.76
    wreck
    0.74
    wagon
    0.74
    crew
    0.73
    ment
    0.71
    bridge
    0.70
    Activations Density 0.008%

    No Known Activations