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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 15961
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software development and technology

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to spirituality and philosophical ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĢ
    -1.30
    vernment
    -1.01
    ÂŃ
    -0.99
    à¼
    -0.93
    ï
    -0.92
    âľ
    -0.87
    COMPLE
    -0.87
    âĢł
    -0.86
    âĹ
    -0.85
     âĢ
    -0.85
    POSITIVE LOGITS
     intrigued
    1.08
     intriguing
    1.05
     resemb
    1.02
     flavours
    0.99
     Interesting
    0.96
     interestingly
    0.96
     interesting
    0.95
     reminiscent
    0.93
     nods
    0.93
     contrasting
    0.93
    Activations Density 0.933%

    No Known Activations