© 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. 17045
    Prev
    Next
    INDEX
    Explanations

    phrases related to aircraft

    oai_token-act-pair · gpt-3.5-turbo

    references to airliners or airline-related topics

    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
     Maw
    -0.60
     Parish
    -0.59
    »Ĵ
    -0.59
     pu
    -0.59
     Batt
    -0.57
     Soci
    -0.56
    itable
    -0.56
     Equ
    -0.55
     digital
    -0.55
     Scottish
    -0.55
    POSITIVE LOGITS
    liner
    4.66
    liners
    4.25
    lining
    2.58
    line
    1.97
     liner
    1.81
    lines
    1.75
    lined
    1.65
    LIN
    1.40
     lin
    1.35
    LINE
    1.24
    Activations Density 0.013%

    No Known Activations