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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 22046
    Prev
    Next
    INDEX
    Explanations

    words related to the Swedish language

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the Swedish word "ör," particularly in variances like its repetitions and usage in contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Crusader
    -0.73
     Bengal
    -0.71
    Brave
    -0.68
     Watson
    -0.66
    ORED
    -0.65
     Catalyst
    -0.63
    Mob
    -0.63
    orers
    -0.63
     Hercules
    -0.62
     Cavaliers
    -0.62
    POSITIVE LOGITS
    ö
    1.12
    ör
    1.12
    andom
    1.02
    ð
    1.02
    ön
    0.97
    ü
    0.92
    sson
    0.88
    án
    0.87
    ä
    0.86
    los
    0.84
    Activations Density 0.004%

    No Known Activations