© 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. 4-RES-JB
    11. 22449
    Prev
    Next
    INDEX
    Explanations

    words that start with the letter "z" followed by a number indicating the strength of activation

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the letter 'z' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •words starting with z

    No Comments

    Negative Logits
    tenance
    -0.81
     minded
    -0.73
    mingham
    -0.72
    TAIN
    -0.70
     compe
    -0.69
     Staples
    -0.69
     Lumpur
    -0.69
     Sut
    -0.67
     Lauder
    -0.67
     attribution
    -0.67
    POSITIVE LOGITS
    ebra
    1.19
    eros
    1.13
    ooming
    1.07
    ipped
    1.06
    odiac
    1.03
    ither
    1.02
    ipp
    0.96
    oned
    0.94
    ipping
    0.94
    anz
    0.92
    Activations Density 0.015%

    No Known Activations