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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8-RES-JB
    6. 5518
    Prev
    Next
    INDEX
    Explanations

    the word "ľ."

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the character 'ľ' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reflex
    -0.88
     favor
    -0.80
     shape
    -0.78
     favour
    -0.77
     synerg
    -0.74
     domest
    -0.74
     morph
    -0.73
     pri
    -0.73
     ornament
    -0.71
     territorial
    -0.71
    POSITIVE LOGITS
    ccording
    1.24
    ï¸ı
    1.22
    Because
    1.10
    There
    1.05
    It
    1.05
    Originally
    1.02
    These
    1.00
    This
    0.99
    They
    0.99
    Sometimes
    0.99
    Activations Density 0.113%

    No Known Activations