© 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. 16151
    Prev
    Next
    INDEX
    Explanations

    the word "Nag" followed by a single-digit number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Nagorno"

    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
    xual
    -0.91
     roy
    -0.75
    terday
    -0.72
    PsyNetMessage
    -0.65
     Serious
    -0.62
     toget
    -0.62
    200000
    -0.61
     Xavier
    -0.61
     Neptune
    -0.59
    clus
    -0.59
    POSITIVE LOGITS
    asaki
    1.27
    oya
    1.15
    ril
    1.08
    atsuki
    1.03
    orno
    1.02
    ourney
    0.97
    lins
    0.92
    rl
    0.91
     Hamm
    0.91
    ash
    0.90
    Activations Density 0.027%

    No Known Activations