© 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. 3202
    Prev
    Next
    INDEX
    Explanations

    locations where things are made or manufactured

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the origin or production details of items

    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
     Unsure
    -0.76
    spons
    -0.72
     VIDEOS
    -0.72
    rants
    -0.70
    ertain
    -0.69
    bernatorial
    -0.68
    lishes
    -0.68
    Interstitial
    -0.66
    ews
    -0.66
    waves
    -0.66
    POSITIVE LOGITS
     meticulous
    0.91
     collaboration
    0.90
     painstaking
    0.86
     Studio
    0.85
     situ
    0.74
     haste
    0.74
     resin
    0.73
     clay
    0.72
    illet
    0.71
     studio
    0.70
    Activations Density 0.380%

    No Known Activations