© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 3074
    Prev
    Next
    INDEX
    Explanations

    specific sequences of characters (likely punctuation) indicating emphasis or special meaning

    oai_token-act-pair · gpt-3.5-turbo

    repeated use of a particular character or symbol

    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
     incorpor
    -0.73
     disadvant
    -0.69
     clitor
    -0.68
     mounts
    -0.68
     vulner
    -0.66
     synerg
    -0.65
     conduc
    -0.64
     altern
    -0.64
     Vaugh
    -0.64
     perspect
    -0.63
    POSITIVE LOGITS
    ï¸ı
    1.31
    âĶĢâĶĢ
    0.91
    §
    0.85
    ternity
    0.84
    âĸł
    0.80
    âĢİ
    0.80
    à¼
    0.79
    ×Ķ
    0.79
    Û
    0.78
    ihad
    0.77
    Activations Density 0.165%

    No Known Activations