© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 24207
    Prev
    Next
    INDEX
    Explanations

    phrases related to aviation

    oai_token-act-pair · gpt-3.5-turbo

    references to aviation and related regulatory bodies

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

    No Comments

    Negative Logits
    ":""},{"
    -0.85
    orah
    -0.85
    gling
    -0.78
    heimer
    -0.76
    utsche
    -0.74
    hips
    -0.72
    ifier
    -0.71
    ãĥİ
    -0.71
    kai
    -0.69
    abase
    -0.68
    POSITIVE LOGITS
     Aviation
    0.91
     hangar
    0.88
    wings
    0.84
     aviation
    0.84
     buffs
    0.81
    querque
    0.79
     Spit
    0.78
     suprem
    0.76
     wing
    0.75
     accidents
    0.75
    Activations Density 0.009%

    No Known Activations