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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 18540
    Prev
    Next
    INDEX
    Explanations

    instructions related to computer programming and memory management

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and concepts related to computer architecture and instruction sets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -1.07
    hur
    -0.84
    gur
    -0.82
    arak
    -0.74
    taboola
    -0.72
    rir
    -0.70
    ean
    -0.70
    JA
    -0.69
     Hos
    -0.68
     experien
    -0.67
    POSITIVE LOGITS
     pointer
    1.13
     bytes
    1.05
     ptr
    0.95
     byte
    0.89
    addr
    0.88
     Width
    0.87
     bits
    0.87
     Header
    0.87
     offset
    0.86
     header
    0.86
    Activations Density 0.196%

    No Known Activations