© 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. 4133
    Prev
    Next
    INDEX
    Explanations

    terms related to the process of screening, especially in contexts like drug screening, airport security screening, and film screening

    oai_token-act-pair · gpt-3.5-turbo

    references to the process of screening

    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
     @@
    -0.73
     disob
    -0.67
    onian
    -0.65
    gey
    -0.65
     Obj
    -0.63
     Ether
    -0.63
     Ele
    -0.63
    warm
    -0.62
     Sr
    -0.62
    god
    -0.61
    POSITIVE LOGITS
     screening
    3.82
     screenings
    3.06
     screened
    2.39
     Screen
    1.69
     vetting
    1.69
     screens
    1.47
     scanning
    1.32
    Screen
    1.31
     profiling
    1.30
    screen
    1.30
    Activations Density 0.021%

    No Known Activations