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. 23227
    Prev
    Next
    INDEX
    Explanations

    numerical measurements and technical details related to various physical objects or devices

    oai_token-act-pair · gpt-3.5-turbo

    specifications and measurements related to physical products

    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
    ãģĹ
    -0.64
     Austral
    -0.63
    OPLE
    -0.62
    ukong
    -0.60
     Gods
    -0.60
     weaknesses
    -0.59
    omever
    -0.58
     licens
    -0.57
    Reloaded
    -0.56
    à¨
    -0.56
    POSITIVE LOGITS
    iameter
    0.73
     GDDR
    0.68
     weighs
    0.67
    izont
    0.66
     increments
    0.66
     Unloaded
    0.65
     diameter
    0.64
     height
    0.64
     Blvd
    0.64
     Width
    0.63
    Activations Density 0.340%

    No Known Activations