© 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. 7540
    Prev
    Next
    INDEX
    Explanations

    results related to Unicode characters or special characters with accents

    oai_token-act-pair · gpt-3.5-turbo

    a specific character or symbol representation, likely related to a particular identity

    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
    iflower
    -0.76
    ITNESS
    -0.75
     Commodore
    -0.73
    WARD
    -0.69
     Coliseum
    -0.68
    ulators
    -0.65
    bury
    -0.64
     Leilan
    -0.63
     DMV
    -0.62
    builders
    -0.62
    POSITIVE LOGITS
    ı
    1.34
    ¼
    1.33
    ½
    1.27
    ł
    1.24
    ¾
    1.22
    ĭ
    1.21
    Ĵ
    1.20
    Į
    1.15
    ĵ
    1.15
    ¤
    1.15
    Activations Density 0.012%

    No Known Activations