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. 8-RES-JB
    6. 18782
    Prev
    Next
    INDEX
    Explanations

    technical terms related to processes or actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to actions, processes, and administrative aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Typh
    -0.64
     Roses
    -0.63
    senal
    -0.63
    Ever
    -0.59
     murdering
    -0.58
     Ta
    -0.57
    NEWS
    -0.56
     Aires
    -0.56
    Tax
    -0.56
    Blood
    -0.56
    POSITIVE LOGITS
     requirement
    0.90
     mechanism
    0.88
     consisted
    0.87
     ensures
    0.86
     consists
    0.85
     lasts
    0.84
     signifies
    0.84
     entails
    0.83
     includes
    0.81
     expires
    0.81
    Activations Density 0.471%

    No Known Activations