© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9493
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cabin"

    oai_token-act-pair · gpt-3.5-turbo

    references to cabins and cockpits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    govtrack
    -0.81
    ku
    -0.77
    Ô
    -0.73
    igers
    -0.73
    UGC
    -0.70
    oppable
    -0.69
    GG
    -0.69
    hitting
    -0.69
    efer
    -0.68
    uality
    -0.68
    POSITIVE LOGITS
     cabin
    1.03
    etry
    0.94
     liner
    0.94
     compartment
    0.93
    artment
    0.84
    lain
    0.82
     quarters
    0.80
     hatch
    0.78
     attendants
    0.77
     Seat
    0.77
    Activations Density 0.047%

    No Known Activations