© 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. 10-RES-JB
    11. 18710
    Prev
    Next
    INDEX
    Explanations

    scientific biological terms, specifically Latin binomial names of plants and animals

    oai_token-act-pair · gpt-3.5-turbo

    terms related to marine biology and aquatic species

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Points
    -0.73
     GEAR
    -0.68
     Boards
    -0.68
    Money
    -0.66
    soDeliveryDate
    -0.66
    MET
    -0.65
    KING
    -0.65
    Quotes
    -0.64
    Daily
    -0.63
     Points
    -0.63
    POSITIVE LOGITS
    ensis
    1.69
    atus
    1.24
    iatus
    1.16
    iens
    1.15
    icus
    1.13
    icum
    1.11
    iae
    1.09
    anus
    1.08
    orum
    1.05
    ii
    1.03
    Activations Density 0.139%

    No Known Activations