© 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. 7-RES-JB
    11. 3514
    Prev
    Next
    INDEX
    Explanations

    genetic and genomic terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to genetics and genomic features

    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
    taboola
    -1.00
    ĪĴ
    -0.98
    ¥µ
    -0.85
    lehem
    -0.81
    ftime
    -0.79
    Vict
    -0.79
     Springs
    -0.78
    ¬¼
    -0.77
    Virgin
    -0.76
    dan
    -0.76
    POSITIVE LOGITS
     gene
    1.15
     genes
    1.14
     mutation
    1.14
     sequencing
    1.11
     polymorph
    1.07
     genome
    1.07
     mutations
    1.06
     genetic
    1.00
     mutated
    0.98
     biologist
    0.97
    Activations Density 0.095%

    No Known Activations