© 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. 3-RES-JB
    11. 9061
    Prev
    Next
    INDEX
    Explanations

    special characters used in coding, specifically the '@' symbol and related expressions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of annotations or tagged elements in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gillespie
    -0.76
     Malk
    -0.74
     Leth
    -0.74
     Torn
    -0.72
     Inquis
    -0.71
    espie
    -0.69
     Ramsey
    -0.68
     Antar
    -0.65
     Morales
    -0.65
     Violet
    -0.64
    POSITIVE LOGITS
    #$
    1.17
    @@@@@@@@
    0.97
    import
    0.92
    gmail
    0.88
    home
    0.87
    param
    0.84
    example
    0.79
    @@@@
    0.79
    oga
    0.78
    include
    0.78
    Activations Density 0.018%

    No Known Activations