© 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. 21089
    Prev
    Next
    INDEX
    Explanations

    the name "Graz" or similar variations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Raz" or related variations

    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
     Korea
    -0.73
     Pompe
    -0.69
     Pwr
    -0.69
     MacArthur
    -0.67
     Latin
    -0.65
     motto
    -0.64
    ADS
    -0.64
     ROM
    -0.62
     Somali
    -0.62
     locality
    -0.61
    POSITIVE LOGITS
    raz
    1.03
    xual
    1.01
    hou
    0.99
    ombie
    0.96
    ere
    0.95
    icz
    0.94
    ese
    0.93
    ombies
    0.93
    quez
    0.92
    hu
    0.92
    Activations Density 0.006%

    No Known Activations