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. 6-RES-JB
    6. 18533
    Prev
    Next
    INDEX
    Explanations

    phrases related to setting goals and intentions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express an objective or goal

    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
     notes
    -0.68
     legends
    -0.67
     hints
    -0.66
     Tide
    -0.65
     legend
    -0.62
     serpent
    -0.61
     Tales
    -0.60
    sen
    -0.60
     Slip
    -0.60
     Fault
    -0.59
    POSITIVE LOGITS
     maximizing
    0.91
     maximize
    0.79
    thood
    0.77
    lessly
    0.77
     preserving
    0.75
     revenge
    0.75
     designing
    0.74
     restoring
    0.73
     erad
    0.71
     achieving
    0.70
    Activations Density 0.185%

    No Known Activations