© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 13382
    Prev
    Next
    INDEX
    Explanations

    specific mentions of adding something to a collection or set

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "add" and its variations, indicating a focus on the concept of addition or inclusion

    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
    CBC
    -0.78
    Application
    -0.70
    Consumer
    -0.68
    SHARE
    -0.65
    Business
    -0.63
    Compare
    -0.62
    ãĤ¡
    -0.62
    JECT
    -0.62
    Returns
    -0.62
    GES
    -0.61
    POSITIVE LOGITS
     flair
    0.91
     thereto
    0.87
     dots
    0.85
     layers
    0.83
     layer
    0.81
    endum
    0.79
     reinforcements
    0.77
     onto
    0.75
     insult
    0.75
     suffix
    0.72
    Activations Density 0.169%

    No Known Activations