© 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. 6-RES-JB
    11. 3542
    Prev
    Next
    INDEX
    Explanations

    names and surnames, particularly the surname "Roth."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, primarily focusing on the name "Roth"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Demand
    -0.70
    tics
    -0.65
    auga
    -0.64
     Tian
    -0.63
     installing
    -0.61
     superintendent
    -0.60
     Cortana
    -0.60
     Tibet
    -0.60
    Ŀ
    -0.59
     Totem
    -0.58
    POSITIVE LOGITS
    bard
    1.24
    stein
    1.17
    bart
    1.02
    igan
    0.98
    cliffe
    0.91
    mans
    0.88
    hea
    0.88
    heit
    0.86
    mund
    0.85
    wald
    0.84
    Activations Density 0.021%

    No Known Activations