© 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. 4-RES-JB
    11. 17160
    Prev
    Next
    INDEX
    Explanations

    references to vacations or trips

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "vacation"

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

    No Comments

    Negative Logits
    ioch
    -0.76
    efficients
    -0.69
     circumst
    -0.68
     Flavoring
    -0.66
    ourke
    -0.65
    ifice
    -0.64
    rencies
    -0.64
    ector
    -0.64
    metics
    -0.62
    rity
    -0.61
    POSITIVE LOGITS
     vacation
    1.09
     vacations
    1.05
     rentals
    0.92
     Vac
    0.85
    oleon
    0.76
    cation
    0.75
     touring
    0.73
     resorts
    0.68
     abroad
    0.68
    spection
    0.67
    Activations Density 0.016%

    No Known Activations