© 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. 24543
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to biological classification, specifically family and genus names

    oai_token-act-pair · gpt-3.5-turbo

    references to biological family classifications

    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
    osta
    -0.91
    igo
    -0.79
    psey
    -0.70
    ipeg
    -0.68
     Advocate
    -0.68
    pee
    -0.68
    yers
    -0.68
    igslist
    -0.66
    arel
    -0.65
    LV
    -0.65
    POSITIVE LOGITS
     genus
    0.94
    lies
    0.85
     resemb
    0.82
    uay
    0.82
    aceae
    0.77
     phyl
    0.76
     resemblance
    0.72
     name
    0.70
    atics
    0.67
     compositions
    0.66
    Activations Density 0.062%

    No Known Activations