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. 9-RES-JB
    6. 2217
    Prev
    Next
    INDEX
    Explanations

    ASCII characters that are not commonly found in regular text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disadvant
    -0.89
     mathemat
    -0.85
     incorpor
    -0.84
     predec
    -0.82
     lawy
    -0.79
     fodder
    -0.78
     filler
    -0.76
     satell
    -0.74
     chunks
    -0.73
     synerg
    -0.72
    POSITIVE LOGITS
    ï¸ı
    1.81
     âĢº
    1.22
    âĢ
    1.19
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    1.17
    âĶĢâĶĢâĶĢâĶĢ
    1.08
    à¥
    1.05
    âĻ
    1.02
    âĶĢâĶĢ
    1.02
    女
    0.99
    âĹ
    0.98
    Activations Density 0.194%

    No Known Activations