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. 4-RES-JB
    6. 23804
    Prev
    Next
    INDEX
    Explanations

    phrases related to intentions

    oai_token-act-pair · gpt-3.5-turbo

    statements regarding personal or organizational intentions

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

    No Comments

    Negative Logits
    cit
    -0.88
     Tycoon
    -0.76
    java
    -0.74
    apple
    -0.70
     Wolves
    -0.69
     Kerr
    -0.66
    hetti
    -0.64
    gars
    -0.64
    tex
    -0.64
     Medals
    -0.62
    POSITIVE LOGITS
    ality
    0.94
     intent
    0.85
    reprene
    0.84
    edIn
    0.82
     intentions
    0.80
     intention
    0.80
    lessly
    0.77
    fulness
    0.77
    edly
    0.76
     guiActiveUn
    0.75
    Activations Density 0.011%

    No Known Activations