© 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. 3-RES-JB
    11. 1561
    Prev
    Next
    INDEX
    Explanations

    phrases related to airlines or aviation

    oai_token-act-pair · gpt-3.5-turbo

    references to jet aircraft or related industry terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģį
    -0.79
    hips
    -0.76
    Ô
    -0.76
    ndum
    -0.73
    \\\\\\\\
    -0.73
    Interstitial
    -0.71
    sembly
    -0.70
    UME
    -0.68
    \\\\\\\\\\\\\\\\
    -0.68
    ACA
    -0.68
    POSITIVE LOGITS
    Jet
    1.05
     Jet
    0.92
     Airways
    0.89
    jet
    0.84
    Fan
    0.75
    zeb
    0.75
    pack
    0.71
    packs
    0.68
     Polo
    0.68
    oleon
    0.67
    Activations Density 0.006%

    No Known Activations