Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 23755
    Prev
    Next
    INDEX
    Explanations

    technical terms related to memory management in computer systems

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and concepts related to memory management and programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    podcast
    -0.89
     Alexis
    -0.82
     Sau
    -0.81
    ":{"
    -0.78
     Brittany
    -0.78
     Hutch
    -0.76
    Social
    -0.75
     Herrera
    -0.74
    âĺħ
    -0.73
    ampunk
    -0.72
    POSITIVE LOGITS
     byte
    1.40
     heap
    1.38
     bytes
    1.38
     ptr
    1.35
     memory
    1.32
     pointer
    1.30
    alloc
    1.26
     Byte
    1.25
     sizeof
    1.24
     pointers
    1.24
    Activations Density 0.423%

    No Known Activations