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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 5539
    Prev
    Next
    INDEX
    Explanations

    references to trips or vacations

    oai_token-act-pair · gpt-3.5-turbo

    references to travel or trips

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =#
    -0.61
    tymology
    -0.60
     relational
    -0.59
     taxp
    -0.57
     substantive
    -0.57
     pulp
    -0.56
    rpm
    -0.55
    respect
    -0.54
     Pie
    -0.54
     CTR
    -0.53
    POSITIVE LOGITS
     itiner
    1.05
     abroad
    1.03
    ods
    0.94
    visor
    0.93
    wire
    0.87
    ogue
    0.86
     planner
    0.79
    trip
    0.79
     trip
    0.76
    engers
    0.75
    Activations Density 0.042%

    No Known Activations