© 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. 20889
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific person's last name, "Fisher"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Fisher."

    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
    oldemort
    -0.73
    terday
    -0.72
     crawl
    -0.71
    xual
    -0.69
    olkien
    -0.68
    ablishment
    -0.65
    umbn
    -0.62
    PsyNetMessage
    -0.62
     sight
    -0.62
    RPG
    -0.61
    POSITIVE LOGITS
    lings
    0.97
    sonian
    0.97
    berg
    0.93
    man
    0.93
    ling
    0.89
     Fisher
    0.89
    strom
    0.87
    ota
    0.85
    folk
    0.83
    mann
    0.81
    Activations Density 0.007%

    No Known Activations