© 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. 4-RES-JB
    11. 20895
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sector"

    oai_token-act-pair · gpt-3.5-turbo

    references to economic sectors

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

    No Comments

    Negative Logits
    fet
    -0.70
    xes
    -0.66
     Booth
    -0.66
     slee
    -0.65
    gdala
    -0.65
    gers
    -0.64
    json
    -0.64
     Brunswick
    -0.61
    sterdam
    -0.60
    aina
    -0.59
    POSITIVE LOGITS
     sectors
    0.99
     sector
    0.95
    sector
    0.92
    umin
    0.81
    enaries
    0.78
     Sector
    0.77
     guiActiveUnfocused
    0.74
    naires
    0.74
    ftime
    0.73
    al
    0.73
    Activations Density 0.010%

    No Known Activations