© 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. 0-RES-JB
    11. 2937
    Prev
    Next
    INDEX
    Explanations

    verbs related to flying or travel by aircraft

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "flown."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Creat
    -0.68
     Soda
    -0.66
     Pot
    -0.66
     remedies
    -0.65
     affirmative
    -0.64
     gent
    -0.63
     demographic
    -0.63
     Carm
    -0.63
     index
    -0.60
    hibition
    -0.60
    POSITIVE LOGITS
     flown
    3.79
     flew
    2.68
     fly
    1.90
     flying
    1.89
    Flying
    1.70
     flies
    1.66
    Flight
    1.65
     helicop
    1.59
     flights
    1.58
    flying
    1.56
    Activations Density 0.012%

    No Known Activations