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. 6-RES-JB
    6. 13110
    Prev
    Next
    INDEX
    Explanations

    the word "that" followed by a dash and an upward arrow symbol

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "âĢ"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rag
    -0.77
     ropes
    -0.65
     Marshal
    -0.64
     gossip
    -0.62
     salad
    -0.62
     curses
    -0.62
     Jav
    -0.61
     snacks
    -0.61
     salads
    -0.61
     Droid
    -0.61
    POSITIVE LOGITS
    º
    1.12
    ¹
    1.04
    Ĵ
    1.00
    £
    0.92
    ®
    0.88
    ķ
    0.88
    ¼
    0.87
    ı
    0.87
    ¡
    0.87
    ates
    0.85
    Activations Density 0.068%

    No Known Activations