© 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. 6306
    Prev
    Next
    INDEX
    Explanations

    activation landmarks representing technical instructions or coding snippets

    oai_token-act-pair · gpt-3.5-turbo

    punctuations and formatting elements used in headings or emphasis

    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
     prosec
    -0.71
    hower
    -0.71
     bicycl
    -0.70
    abwe
    -0.70
     volunteered
    -0.69
     occupation
    -0.69
     Eisenhower
    -0.67
     crosses
    -0.67
     Roosevelt
    -0.66
    ewater
    -0.65
    POSITIVE LOGITS
    Samsung
    1.27
    Sony
    1.25
    Android
    1.16
    Xbox
    1.13
    Nintendo
    1.13
    Speaking
    1.12
    Exit
    1.05
     Razer
    1.05
     Xperia
    1.03
    LG
    1.02
    Activations Density 0.513%

    No Known Activations