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. 2-RES-JB
    6. 327
    Prev
    Next
    INDEX
    Explanations

    particular special characters or diacritics in text, with a preference for the character "ê" and to some extent "è"

    oai_token-act-pair · gpt-4-turbo

    special characters and non-English characters, with a focus on the character 'ê'

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uctor
    -1.00
    Reviewer
    -0.77
    iaries
    -0.77
     guiActiveUn
    -0.73
    iary
    -0.73
    inarily
    -0.70
    ometimes
    -0.70
    ennial
    -0.69
    emonium
    -0.69
    ativity
    -0.68
    POSITIVE LOGITS
    ²
    1.24
    ¹
    1.21
    °
    1.16
    ¾
    1.14
    ¶
    1.11
    ¼
    1.08
    ¸
    1.06
    ½
    1.05
    ³
    1.03
    ·
    1.01
    Activations Density 0.003%

    No Known Activations