© 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. 2426
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or settings within social situations

    oai_token-act-pair · gpt-3.5-turbo

    references to people's presence and roles in specific contexts

    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
     partName
    -0.72
    elman
    -0.71
    DERR
    -0.66
     subp
    -0.66
     scroll
    -0.66
    Browser
    -0.63
     Gleaming
    -0.62
    asel
    -0.62
    aler
    -0.60
     reverted
    -0.60
    POSITIVE LOGITS
    DonaldTrump
    0.72
     roofs
    0.70
     rooft
    0.68
     orbit
    0.67
     town
    0.66
     equation
    0.65
     whom
    0.64
    veyard
    0.63
     fold
    0.63
     anytime
    0.62
    Activations Density 0.376%

    No Known Activations