© 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. 10-RES-JB
    11. 10997
    Prev
    Next
    INDEX
    Explanations

    the verb "are" followed by some form of a number or specific descriptor

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating quantities or presence of entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -0.74
    inventoryQuantity
    -0.69
     gratification
    -0.67
     Relations
    -0.65
     Desk
    -0.62
     ¯
    -0.59
     Politics
    -0.59
    inav
    -0.59
     Dreams
    -0.58
     slideshow
    -0.58
    POSITIVE LOGITS
     involved
    1.17
     listed
    1.09
     vying
    1.02
     eligible
    1.00
     surveyed
    1.00
     enrolled
    0.99
     available
    0.99
     implicated
    0.98
     employed
    0.95
     affected
    0.95
    Activations Density 0.145%

    No Known Activations