© 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. 6511
    Prev
    Next
    INDEX
    Explanations

    the name "son" that is part of a person's last name

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "son"

    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
     heels
    -0.74
     deficits
    -0.70
    ANN
    -0.67
     chronically
    -0.65
     breaches
    -0.63
     neut
    -0.63
    ASED
    -0.62
     contagious
    -0.60
     probing
    -0.60
    acebook
    -0.60
    POSITIVE LOGITS
    nen
    0.93
    strom
    0.92
    ville
    0.89
    ja
    0.86
    son
    0.85
    osa
    0.85
    ning
    0.84
    fman
    0.83
     Jr
    0.80
    ryu
    0.79
    Activations Density 0.017%

    No Known Activations