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

    Neuronpedia

    Jacobian LensNEW
    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. 1-RES-JB
    11. 21678
    Prev
    Next
    INDEX
    Explanations

    text representations of special characters or symbols

    oai_token-act-pair · gpt-3.5-turbo

    the character 'âĢ' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     detached
    -0.66
    lder
    -0.63
     fragmentation
    -0.62
     semblance
    -0.60
     womb
    -0.60
    ught
    -0.59
     mosqu
    -0.59
    ozy
    -0.59
     transfer
    -0.59
     Roc
    -0.58
    POSITIVE LOGITS
    ij
    0.97
     âĢ
    0.97
    ¹
    0.96
    âĸº
    0.94
    ł
    0.91
    âĢ
    0.87
    IJ
    0.87
    âĢł
    0.84
    ª
    0.83
    âĢķ
    0.82
    Activations Density 0.234%

    No Known Activations