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. 11-RES-JB
    6. 15483
    Prev
    Next
    INDEX
    Explanations

    phrases separated by special characters 'Ċ' within the text

    oai_token-act-pair · gpt-3.5-turbo

    references to media releases and announcements

    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
     eleph
    -1.01
     citiz
    -0.94
    Þ
    -0.81
     occas
    -0.78
    aditional
    -0.76
     exting
    -0.74
     imperson
    -0.73
     tremend
    -0.73
     hemor
    -0.71
     mosqu
    -0.69
    POSITIVE LOGITS
    Fans
    0.91
    Original
    0.86
    iOS
    0.84
    Marvel
    0.81
    NVIDIA
    0.81
    ↵
    0.79
    Previously
    0.79
    Nintendo
    0.79
    Xbox
    0.78
    Update
    0.77
    Activations Density 0.447%

    No Known Activations