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. 7-RES-JB
    6. 10758
    Prev
    Next
    INDEX
    Explanations

    instances where someone gives permission or authorization

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating permission or consent

    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
     Eater
    -0.51
     sear
    -0.50
     Fram
    -0.50
    \":
    -0.50
    ï¸ı
    -0.49
     Nielsen
    -0.46
    yssey
    -0.46
    Journal
    -0.45
    Serial
    -0.45
    ceans
    -0.44
    POSITIVE LOGITS
     subordinate
    0.68
     sacrific
    0.65
     freely
    0.64
     uninterrupted
    0.63
     unim
    0.62
     withdrawn
    0.61
     subord
    0.60
    ardless
    0.58
     unrestricted
    0.57
     uncond
    0.56
    Activations Density 0.951%

    No Known Activations