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. 3-RES-JB
    6. 6695
    Prev
    Next
    INDEX
    Explanations

    words related to maximizing or minimizing something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to minimizing and maximizing strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VIDEO
    -0.74
    RESULTS
    -0.74
    Else
    -0.72
    UGC
    -0.71
     Attorney
    -0.71
    BuyableInstoreAndOnline
    -0.70
    RAW
    -0.69
     Indigo
    -0.66
    Magikarp
    -0.65
     Bath
    -0.64
    POSITIVE LOGITS
    isations
    1.03
    icum
    1.00
    emaker
    0.99
    izes
    0.99
    illian
    0.98
    ises
    0.98
    izations
    0.97
     minim
    0.96
    psons
    0.95
    ilit
    0.94
    Activations Density 0.011%

    No Known Activations