© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 19092
    Prev
    Next
    INDEX
    Explanations

    keywords related to genomic or genetic terms, specifically the suffix "-omes"

    oai_token-act-pair · gpt-3.5-turbo

    references to genetic terms related to chromosomes and their structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     attribute
    -0.63
     NCT
    -0.63
     employee
    -0.62
     Delta
    -0.61
     reinvest
    -0.59
     credential
    -0.59
     flag
    -0.59
     airliner
    -0.58
     supporter
    -0.58
     ph
    -0.58
    POSITIVE LOGITS
    omes
    4.77
    ome
    2.11
    OME
    1.66
    omic
    1.63
    omal
    1.60
    omers
    1.33
    oms
    1.33
    omics
    1.30
    omen
    1.25
    opes
    1.20
    Activations Density 0.012%

    No Known Activations