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. 521
    Prev
    Next
    INDEX
    Explanations

    medical terms in Spanish

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with engineering and construction

    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
     decaying
    -0.63
     Winston
    -0.62
     Clause
    -0.61
     poorly
    -0.60
     sticky
    -0.60
     Slaughter
    -0.59
     snail
    -0.58
     Bubble
    -0.58
     Wr
    -0.57
     Forrest
    -0.57
    POSITIVE LOGITS
    ê
    1.27
    ó
    1.19
    ô
    1.19
    ÃŃ
    1.18
    és
    1.17
    ét
    1.16
    én
    1.15
    û
    1.12
    ÃŃa
    1.12
    ã
    1.11
    Activations Density 0.204%

    No Known Activations