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. 9-RES-JB
    6. 12433
    Prev
    Next
    INDEX
    Explanations

    references to the term "drag" used in various contexts, such as drag racing or economic drag

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "drag" and its variations or related context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vironment
    -0.77
     Kubrick
    -0.66
     AVG
    -0.65
     Blueprint
    -0.65
    cium
    -0.62
     Seym
    -0.62
    iber
    -0.62
    VERTISEMENT
    -0.62
    ership
    -0.61
     WARN
    -0.59
    POSITIVE LOGITS
    ged
    0.96
    oon
    0.92
    glers
    0.91
    ging
    0.91
    strip
    0.86
     queens
    0.86
    gers
    0.82
    gin
    0.82
    ster
    0.78
    net
    0.78
    Activations Density 0.047%

    No Known Activations