© 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. 2-RES-JB
    11. 12340
    Prev
    Next
    INDEX
    Explanations

    words related to travel itineraries

    oai_token-act-pair · gpt-3.5-turbo

    references to travel itineraries and plans

    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
    kus
    -0.73
     embryonic
    -0.70
     oxide
    -0.70
    cill
    -0.69
     spelling
    -0.69
     nipples
    -0.68
     fertilizer
    -0.68
     filament
    -0.68
     alloy
    -0.67
     cellul
    -0.67
    POSITIVE LOGITS
    Route
    0.85
    ttes
    0.84
    route
    0.82
     Guests
    0.81
     Wanted
    0.80
     destinations
    0.79
     Countries
    0.78
     itiner
    0.78
    fare
    0.78
     Tours
    0.76
    Activations Density 0.190%

    No Known Activations