© 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. 2-RES-JB
    11. 17369
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Ser" or related to "Serbian"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Serbians

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ORN
    -0.86
    Rated
    -0.85
    INGTON
    -0.84
    ESCO
    -0.76
    AUT
    -0.75
    OWS
    -0.75
    isconsin
    -0.72
    ATS
    -0.71
    INTER
    -0.70
    STEP
    -0.70
    POSITIVE LOGITS
    rha
    0.94
    onial
    0.94
    geant
    0.93
    archs
    0.91
    ials
    0.85
     lapt
    0.83
    otonin
    0.82
     unden
    0.82
    iffs
    0.82
    rano
    0.82
    Activations Density 0.010%

    No Known Activations