© 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. 7140
    Prev
    Next
    INDEX
    Explanations

    text written in a non-English language, specifically featuring the character "ä"

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or symbol

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ORED
    -0.82
     Sussex
    -0.68
     Jericho
    -0.67
     Mayweather
    -0.66
    IFIED
    -0.66
     Bullets
    -0.63
     Hodg
    -0.60
    ################
    -0.59
     Asians
    -0.58
     Notting
    -0.58
    POSITIVE LOGITS
    ä
    1.27
    inen
    1.18
    ¢
    1.10
    ternity
    1.05
    ·
    0.96
    ¯¯¯¯
    0.93
    ¶
    0.93
    ë
    0.91
    ï
    0.90
    ö
    0.88
    Activations Density 0.012%

    No Known Activations