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. 4-RES-JB
    6. 17854
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to information technology

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to significance and authority in various contexts

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

    No Comments

    Negative Logits
     powerful
    -0.60
     aging
    -0.58
     ast
    -0.57
     overcrowd
    -0.56
     mesmer
    -0.55
     knowledgeable
    -0.54
     reliable
    -0.54
     legitimate
    -0.54
     curv
    -0.53
     mans
    -0.53
    POSITIVE LOGITS
    tenance
    1.28
    terday
    1.25
    theless
    1.19
    osterone
    0.87
    etheless
    0.86
    ãĤ´ãĥ³
    0.84
    llor
    0.80
    acters
    0.79
    -+-+
    0.74
    odore
    0.74
    Activations Density 0.327%

    No Known Activations