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. 10-RES-JB
    6. 13407
    Prev
    Next
    INDEX
    Explanations

    technical terms related to systems or processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to structured systems and societal themes

    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
    bia
    -0.67
    etheless
    -0.65
    Ward
    -0.60
    backer
    -0.59
    urther
    -0.58
    remlin
    -0.58
    ãģ®ç
    -0.57
    ãĤ¦
    -0.55
    imeo
    -0.55
    nea
    -0.54
    POSITIVE LOGITS
     consisting
    1.23
     alternating
    0.92
     divided
    0.91
     consists
    0.90
     consisted
    0.90
     whereby
    0.90
     consist
    0.87
     averaging
    0.86
     wherein
    0.86
     whereas
    0.84
    Activations Density 0.750%

    No Known Activations