© 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. 10646
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically surnames

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly those related to a specific context or event

    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
     pride
    -0.67
     Sussex
    -0.66
     Curse
    -0.61
     swamp
    -0.59
     Indians
    -0.58
     dividend
    -0.57
     slack
    -0.56
     Naruto
    -0.56
     graffiti
    -0.55
     tyre
    -0.55
    POSITIVE LOGITS
    mann
    1.79
    strom
    1.58
    feld
    1.54
    lund
    1.49
    gren
    1.46
    berg
    1.46
    meyer
    1.43
    quist
    1.42
    baum
    1.41
    stein
    1.38
    Activations Density 0.102%

    No Known Activations