© 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. 9-RES-JB
    11. 7466
    Prev
    Next
    INDEX
    Explanations

    words that start with the letter 'n'

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the letter 'n'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.73
     welf
    -0.58
    eering
    -0.58
     laun
    -0.57
     Carbuncle
    -0.57
     incent
    -0.57
    draw
    -0.57
     caution
    -0.57
     Ãľ
    -0.56
     frank
    -0.56
    POSITIVE LOGITS
    aturally
    1.17
    uggets
    1.14
    ovation
    1.12
    umerous
    1.11
    orthern
    1.10
    ihil
    1.08
    vironment
    1.05
    ucle
    1.05
    aughty
    1.04
    ounced
    1.01
    Activations Density 0.061%

    No Known Activations