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. 24441
    Prev
    Next
    INDEX
    Explanations

    targets related to specific goals or objectives

    oai_token-act-pair · gpt-3.5-turbo

    phrases describing objectives or goals

    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
    Guard
    -0.78
    note
    -0.74
    minus
    -0.73
    acted
    -0.72
    guards
    -0.70
    shit
    -0.64
    outside
    -0.64
    chapter
    -0.63
    hot
    -0.62
    part
    -0.62
    POSITIVE LOGITS
     maximizing
    0.91
     perfection
    0.90
     maximize
    0.88
     achieving
    0.84
     achieve
    0.84
     emulate
    0.84
     replicate
    0.82
     minimize
    0.79
     improving
    0.79
     recreate
    0.77
    Activations Density 0.164%

    No Known Activations