© 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. 9371
    Prev
    Next
    INDEX
    Explanations

    phrases related to aviation and piloting

    oai_token-act-pair · gpt-3.5-turbo

    words related to piloting or flying

    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
    anwhile
    -0.93
     Carbuncle
    -0.88
     EntityItem
    -0.72
    upon
    -0.70
     Dwell
    -0.66
     Debor
    -0.66
    lies
    -0.63
     Byr
    -0.63
     END
    -0.61
    ires
    -0.61
    POSITIVE LOGITS
    crow
    1.06
    wings
    0.99
    cone
    0.92
    chers
    0.92
    oted
    0.92
    ots
    0.89
    ando
    0.88
    avement
    0.87
    icate
    0.86
    grim
    0.86
    Activations Density 0.019%

    No Known Activations