© 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. 23847
    Prev
    Next
    INDEX
    Explanations

    the name "Iz" with varying activations

    oai_token-act-pair · gpt-3.5-turbo

    the word "Iz" and its variations in different contexts

    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
    quartered
    -0.83
     Norn
    -0.76
     srf
    -0.70
     whistle
    -0.70
    riott
    -0.68
    bably
    -0.65
     shroud
    -0.65
    ¥ŀ
    -0.65
     satell
    -0.64
     limp
    -0.62
    POSITIVE LOGITS
    arro
    1.37
    iz
    1.18
    ombie
    0.99
    azz
    0.96
    abel
    0.93
    awa
    0.92
    iaz
    0.91
    ymes
    0.91
    azo
    0.91
    utsu
    0.91
    Activations Density 0.008%

    No Known Activations