© 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. 2-RES-JB
    11. 3253
    Prev
    Next
    INDEX
    Explanations

    phrases related to locations, particularly the airport "Gatwick"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Gat" and variations thereof in various contexts

    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
    perse
    -0.71
     ancest
    -0.69
     brow
    -0.65
    egg
    -0.65
     deposition
    -0.64
    LEASE
    -0.62
     shepherd
    -0.62
    domain
    -0.61
    anwhile
    -0.61
    PRES
    -0.61
    POSITIVE LOGITS
     Gat
    1.10
    herer
    1.07
    estone
    0.93
    glers
    0.93
    igue
    0.86
    rop
    0.84
    estones
    0.84
    chet
    0.84
    aret
    0.84
     Pengu
    0.83
    Activations Density 0.005%

    No Known Activations