© 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. 1-RES-JB
    11. 15910
    Prev
    Next
    INDEX
    Explanations

    phrases related to the background of a situation or context

    oai_token-act-pair · gpt-3.5-turbo

    references to "background" related contexts or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ILCS
    -0.72
    NK
    -0.71
    ikh
    -0.70
    cept
    -0.66
    erion
    -0.66
    ishops
    -0.66
    CVE
    -0.66
    ECT
    -0.64
    cial
    -0.64
    ribut
    -0.64
    POSITIVE LOGITS
     background
    1.43
     backgrounds
    1.09
     Background
    1.04
    background
    1.01
    coat
    0.94
     backdrop
    0.90
     foreground
    0.85
    tones
    0.83
     bott
    0.71
     drafts
    0.70
    Activations Density 0.009%

    No Known Activations