© 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. 8-RES-JB
    11. 1990
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "gan" with different numerical values

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "gan."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Britann
    -0.64
    ractive
    -0.64
    ension
    -0.63
    ensions
    -0.62
    İĭ
    -0.61
     Cind
    -0.61
     zo
    -0.60
    suit
    -0.58
     differential
    -0.58
    acter
    -0.57
    POSITIVE LOGITS
    igans
    1.04
    za
    0.99
    igan
    0.97
    agher
    0.93
    cia
    0.90
    culosis
    0.89
    istan
    0.88
    gha
    0.87
    omics
    0.85
    ogly
    0.85
    Activations Density 0.028%

    No Known Activations