© 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. 8-RES-JB
    11. 22421
    Prev
    Next
    INDEX
    Explanations

    references to modes of transportation, specifically trains

    oai_token-act-pair · gpt-3.5-turbo

    references to trains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osi
    -0.70
     Tablet
    -0.69
     Sphere
    -0.68
    erenn
    -0.67
     Reach
    -0.62
     pop
    -0.62
     Prairie
    -0.60
    cised
    -0.60
     alien
    -0.58
    metics
    -0.58
    POSITIVE LOGITS
    wreck
    1.28
    roads
    1.02
    loads
    1.00
     conductor
    1.00
    ees
    0.97
    cars
    0.92
     wreck
    0.89
     cars
    0.88
     locom
    0.85
     trains
    0.85
    Activations Density 0.033%

    No Known Activations