© 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. 4-RES-JB
    11. 7614
    Prev
    Next
    INDEX
    Explanations

    phrases containing the symbol "âĢ"

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of a specific symbol or character

    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
    creen
    -0.74
    anwhile
    -0.67
     Roc
    -0.64
    ammy
    -0.63
    ctors
    -0.63
     Meter
    -0.61
     reception
    -0.60
     dust
    -0.60
    ozy
    -0.59
     Somerset
    -0.58
    POSITIVE LOGITS
    âĹ¼
    1.00
    âĢł
    0.88
    ¹
    0.87
    0.82
    ¯
    0.79
    ¬
    0.79
    Order
    0.75
    §
    0.75
    Footnote
    0.73
    Versions
    0.72
    Activations Density 0.505%

    No Known Activations