© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 23976
    Prev
    Next
    INDEX
    Explanations

    references to negotiations or conversations between different parties or individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "between."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gow
    -0.78
    OGR
    -0.78
    inventoryQuantity
    -0.76
     teasp
    -0.75
    iken
    -0.75
    nit
    -0.74
    unc
    -0.74
    TPPStreamerBot
    -0.73
    spect
    -0.72
    ãĤ¤ãĥĪ
    -0.71
    POSITIVE LOGITS
     sexes
    0.88
     Israelis
    0.85
     factions
    0.85
     genders
    0.84
     combatants
    0.80
     Kore
    0.78
     friends
    0.75
     halves
    0.74
     spouses
    0.73
     strangers
    0.73
    Activations Density 0.045%

    No Known Activations