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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 23648
    Prev
    Next
    INDEX
    Explanations

    mentions of "background" as related to personal history or investigative checks

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "background"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ikh
    -0.76
     ILCS
    -0.72
    cery
    -0.65
    NK
    -0.65
    hof
    -0.62
    thing
    -0.62
    missible
    -0.61
    rs
    -0.61
    erion
    -0.61
    ishable
    -0.60
    POSITIVE LOGITS
     background
    1.15
     backgrounds
    0.99
     Background
    0.97
    coat
    0.91
    background
    0.81
     backdrop
    0.74
     checks
    0.72
     Checks
    0.69
    GROUND
    0.65
     foreground
    0.65
    Activations Density 0.011%

    No Known Activations