© 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. 20952
    Prev
    Next
    INDEX
    Explanations

    the prefix "iz" within words

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "iz"

    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
     Norn
    -0.86
     whistle
    -0.76
    quartered
    -0.74
     handshake
    -0.70
     srf
    -0.69
     satell
    -0.67
     prostitute
    -0.66
     flock
    -0.66
     concession
    -0.65
    riott
    -0.65
    POSITIVE LOGITS
    iz
    1.40
    arro
    1.22
    azz
    1.11
    azo
    1.02
    iaz
    0.99
    abel
    0.98
    ombie
    0.96
    az
    0.95
    cz
    0.93
    ihad
    0.92
    Activations Density 0.006%

    No Known Activations