© 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. 11-RES-JB
    11. 7539
    Prev
    Next
    INDEX
    Explanations

    German words or phrases beginning with 'z'

    oai_token-act-pair · gpt-3.5-turbo

    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 @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ModLoader
    -0.72
     foremost
    -0.61
     competitors
    -0.57
     besides
    -0.56
     minded
    -0.56
     competing
    -0.56
     robbing
    -0.55
     commute
    -0.55
     Choice
    -0.54
    WAYS
    -0.54
    POSITIVE LOGITS
    odiac
    1.29
    ebra
    1.29
    ealous
    1.28
    ijn
    1.17
    iggurat
    1.07
    immer
    1.06
    anz
    1.05
    onal
    1.04
    ooming
    1.02
    anza
    1.00
    Activations Density 0.020%

    No Known Activations