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. 7-RES-JB
    6. 7559
    Prev
    Next
    INDEX
    Explanations

    phrases containing proper nouns or specific names, potentially related to news or social media posts

    oai_token-act-pair · gpt-3.5-turbo

    the presence of end-of-document markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exha
    -0.82
     hemor
    -0.77
     tradem
    -0.76
     grounding
    -0.74
     withd
    -0.71
     metic
    -0.70
     disadvant
    -0.70
     volunte
    -0.70
     deliveries
    -0.70
     manif
    -0.69
    POSITIVE LOGITS
    taboola
    1.01
    NET
    0.98
    jpg
    0.94
    embed
    0.90
    htm
    0.86
    webkit
    0.85
    html
    0.85
    php
    0.82
    mp
    0.80
    title
    0.78
    Activations Density 0.043%

    No Known Activations