© 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. 8674
    Prev
    Next
    INDEX
    Explanations

    the name "Daljit" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Dal" followed by various numeric associations

    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
    éĹĺ
    -0.80
     Lovecraft
    -0.78
    ItemTracker
    -0.76
    hift
    -0.73
    sburgh
    -0.70
     Parenthood
    -0.69
     Collider
    -0.65
     Archangel
    -0.64
    inventoryQuantity
    -0.62
     ESC
    -0.62
    POSITIVE LOGITS
    inar
    1.09
    pling
    0.97
    vik
    0.92
    istry
    0.91
    mor
    0.91
    jan
    0.90
    der
    0.90
    adier
    0.88
    rill
    0.87
    iber
    0.87
    Activations Density 0.019%

    No Known Activations