© 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. 2-RES-JB
    11. 17071
    Prev
    Next
    INDEX
    Explanations

    generic coding syntax characters often used in programming

    oai_token-act-pair · gpt-3.5-turbo

    special characters or formatting conventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guid
    -0.69
     disav
    -0.67
     disposable
    -0.65
     plank
    -0.64
     sacrific
    -0.63
     conversion
    -0.63
     sidel
    -0.62
     disappro
    -0.62
     detached
    -0.61
     destroyer
    -0.61
    POSITIVE LOGITS
    taboola
    0.88
    CLASSIFIED
    0.82
    ï¸ı
    0.79
     ®
    0.78
    âĢ¢
    0.76
    ---------
    0.76
    #$
    0.76
    Hart
    0.73
    âĢİ
    0.73
    ©
    0.72
    Activations Density 0.206%

    No Known Activations