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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7502
    Prev
    Next
    INDEX
    Explanations

    references to computer chips

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of chips in technology

    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
    æĢ
    -0.70
     gearing
    -0.68
     Vaj
    -0.66
     Territ
    -0.66
     Canal
    -0.65
     Scandinav
    -0.64
     Refugee
    -0.64
     Stranger
    -0.62
     Parish
    -0.61
     Dayton
    -0.60
    POSITIVE LOGITS
    otle
    1.66
    mun
    1.14
    board
    0.97
    washer
    0.90
    chip
    0.89
    ambers
    0.89
     implanted
    0.89
    Chip
    0.81
     chip
    0.81
    maker
    0.81
    Activations Density 0.039%

    No Known Activations