© 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. 21450
    Prev
    Next
    INDEX
    Explanations

    words containing the letter "z"

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'z' appearing frequently throughout the text

    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
    •words starting with z

    No Comments

    Negative Logits
     Palestin
    -0.74
    mingham
    -0.72
    ulhu
    -0.71
    tenance
    -0.71
    luent
    -0.70
     compe
    -0.70
    licts
    -0.68
    Downloadha
    -0.67
    "]=>
    -0.67
     Lumpur
    -0.66
    POSITIVE LOGITS
    anz
    1.01
    ebra
    0.98
    eros
    0.94
    ooming
    0.90
    odiac
    0.88
    ipped
    0.87
    ither
    0.84
    oon
    0.82
    ipp
    0.81
     z
    0.81
    Activations Density 0.010%

    No Known Activations