© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 7709
    Prev
    Next
    INDEX
    Explanations

    phrases containing unusual characters, which might be used for emphasis or flair in text

    oai_token-act-pair · gpt-3.5-turbo

    the symbol "âĢ" indicating a certain formatting or encoding issue, possibly in relation to significant terms or concepts

    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
     sidx
    -0.69
     Send
    -0.68
     scattering
    -0.68
     Manhattan
    -0.68
     sled
    -0.65
    creen
    -0.64
     Pilgrim
    -0.64
     scatter
    -0.62
     Thy
    -0.61
    anwhile
    -0.61
    POSITIVE LOGITS
    ¬
    1.26
    ľ
    1.05
    ı
    1.03
    ¹
    1.00
    º
    0.96
    »
    0.95
    Ĵ
    0.93
    Į
    0.93
    į
    0.92
    ĭ
    0.89
    Activations Density 0.180%

    No Known Activations