Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 9492
    Prev
    Next
    INDEX
    Explanations

    German characters (such as "ü") within the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the German umlaut character 'ü'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ividual
    -0.78
    ertodd
    -0.72
     Eaton
    -0.67
     Keeper
    -0.67
     Strongh
    -0.65
     fracture
    -0.64
     Luther
    -0.64
     Gems
    -0.63
    assian
    -0.63
     Cobra
    -0.63
    POSITIVE LOGITS
    ¶
    1.06
    ¸
    1.06
    ·
    1.04
    ¿
    1.03
    ü
    1.01
    ĸ
    0.96
    ³
    0.95
    ½
    0.94
    ĺ
    0.93
    ¬
    0.92
    Activations Density 0.007%

    No Known Activations