© 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. 1-RES-JB
    11. 21051
    Prev
    Next
    INDEX
    Explanations

    the name "Ros" with different variations in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific person, likely connected to sports or other notable events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CARE
    -0.68
    ASED
    -0.67
     CPR
    -0.63
     contrasting
    -0.62
     Chinese
    -0.60
     Helpful
    -0.59
     realistic
    -0.58
     syll
    -0.57
     medium
    -0.57
     USC
    -0.57
    POSITIVE LOGITS
    xual
    1.03
    atile
    1.00
    ion
    0.97
    ingen
    0.96
    anus
    0.96
    clerosis
    0.95
    terday
    0.94
    mith
    0.94
    ions
    0.90
    anian
    0.90
    Activations Density 0.004%

    No Known Activations