© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 17275
    Prev
    Next
    INDEX
    Explanations

    code snippets involving C++ iterators and related computational tasks

    oai_token-act-pair · gpt-3.5-turbo

    elements related to C++ programming language structures, specifically around iterators and data types

    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
    soever
    -0.95
    gur
    -0.90
     explan
    -0.88
    uscript
    -0.84
    raq
    -0.82
     mosqu
    -0.82
    jab
    -0.80
    hots
    -0.79
    bots
    -0.77
    ugi
    -0.77
    POSITIVE LOGITS
    ptr
    0.91
     uint
    0.88
     NULL
    0.81
     ptr
    0.79
     unsigned
    0.78
     );
    0.78
     __
    0.76
     /*
    0.76
     seq
    0.75
     Pwr
    0.74
    Activations Density 0.146%

    No Known Activations