© 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. 8-RES-JB
    11. 2586
    Prev
    Next
    INDEX
    Explanations

    technical terms related to online platforms and services

    oai_token-act-pair · gpt-3.5-turbo

    references to online advertising and web services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spe
    -0.68
    ridor
    -0.65
     trail
    -0.63
     trap
    -0.62
     piercing
    -0.62
     preacher
    -0.60
     chamber
    -0.59
     newcomers
    -0.59
     knot
    -0.58
     knit
    -0.58
    POSITIVE LOGITS
    Shop
    0.84
    Xbox
    0.80
     Ltd
    0.77
    artz
    0.75
    merce
    0.74
    ãĤ¼ãĤ¦ãĤ¹
    0.74
    Bench
    0.71
     Graph
    0.70
     patents
    0.68
    Jr
    0.68
    Activations Density 0.279%

    No Known Activations