Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-RES-JB
    6. 2736
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of optimization or achieving the most favorable outcome

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing optimal choices or high-quality options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     todd
    -0.88
    SPONSORED
    -0.82
    avers
    -0.65
    dd
    -0.64
    tags
    -0.61
     Twain
    -0.61
     omin
    -0.61
    ç«
    -0.60
    unts
    -0.60
    ums
    -0.59
    POSITIVE LOGITS
    ibur
    0.90
     bang
    0.88
     outcome
    0.86
     possible
    0.85
     results
    0.85
     outcomes
    0.77
     RO
    0.73
     Results
    0.73
    iator
    0.72
    Quality
    0.70
    Activations Density 0.279%

    No Known Activations