© 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. 7388
    Prev
    Next
    INDEX
    Explanations

    words related to "bi-" prefixes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "bio" related topics or terms

    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
    lain
    -0.84
    AGES
    -0.78
    swick
    -0.74
    âķIJ
    -0.74
    âķIJâķIJ
    -0.74
    MENTS
    -0.74
    oldemort
    -0.68
    witz
    -0.68
    UTION
    -0.67
    OCK
    -0.67
    POSITIVE LOGITS
    ochem
    1.10
    otechnology
    1.07
    omed
    1.07
    omes
    1.06
    ocide
    1.02
    ochemistry
    1.01
    otic
    1.00
    ographical
    0.98
    ophon
    0.97
    odynamic
    0.96
    Activations Density 0.008%

    No Known Activations