© 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. 11395
    Prev
    Next
    INDEX
    Explanations

    references to a specific person, likely related to news or current events

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or groups

    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
    EngineDebug
    -0.81
    WT
    -0.80
     Michaels
    -0.79
    agne
    -0.75
    WAYS
    -0.71
    UGE
    -0.71
    KY
    -0.71
    âķIJâķIJ
    -0.68
     Hanson
    -0.67
    æѦ
    -0.66
    POSITIVE LOGITS
    lique
    1.26
    edience
    1.01
    lig
    0.98
    solete
    0.96
    isphere
    0.96
    olesc
    0.94
    nox
    0.94
    fusc
    0.93
     Ob
    0.92
    omination
    0.90
    Activations Density 0.009%

    No Known Activations