© 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. 4266
    Prev
    Next
    INDEX
    Explanations

    words related to genetic mutations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to genetic mutations

    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
    travel
    -0.79
    ¯¯
    -0.79
    ħĭ
    -0.75
     Aires
    -0.74
    ¥µ
    -0.72
    english
    -0.70
    ¾
    -0.70
    stra
    -0.70
    eger
    -0.69
    ramid
    -0.69
    POSITIVE LOGITS
     mutation
    1.11
     mutations
    0.99
     allele
    0.94
     predis
    0.87
     mutants
    0.85
    ulously
    0.83
     inhibitor
    0.82
     mutated
    0.82
    icides
    0.77
     inhibitors
    0.76
    Activations Density 0.015%

    No Known Activations