© 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. 9-RES-JB
    11. 2892
    Prev
    Next
    INDEX
    Explanations

    mentions of trips or travel-related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to trips or travel experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     taxp
    -0.67
    tymology
    -0.65
    =#
    -0.65
    pta
    -0.64
     Converted
    -0.60
    rity
    -0.59
     substantive
    -0.59
    Percent
    -0.56
    baum
    -0.56
    gae
    -0.56
    POSITIVE LOGITS
     abroad
    0.98
    ods
    0.96
     itiner
    0.95
    ogue
    0.93
    visor
    0.88
    wire
    0.82
     trips
    0.81
     trip
    0.80
    trip
    0.78
    olit
    0.77
    Activations Density 0.036%

    No Known Activations