Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 23969
    Prev
    Next
    INDEX
    Explanations

    mentions of military aircraft, especially fighter jets

    oai_token-act-pair · gpt-3.5-turbo

    references to fighter aircraft

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NRS
    -0.75
    ologies
    -0.73
    ologically
    -0.72
    ological
    -0.70
     Westminster
    -0.69
    imated
    -0.68
    ories
    -0.66
    andre
    -0.65
    eus
    -0.64
    ourced
    -0.63
    POSITIVE LOGITS
     jets
    1.15
     jet
    1.06
     pilots
    0.95
    fighters
    0.87
    fighter
    0.82
    selage
    0.80
     squadron
    0.79
     Typhoon
    0.79
    fighting
    0.78
     pilot
    0.76
    Activations Density 0.046%

    No Known Activations