© 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. 11-RES-JB
    11. 16474
    Prev
    Next
    INDEX
    Explanations

    quantitative information such as numbers, measurements, and quantities

    oai_token-act-pair · gpt-3.5-turbo

    phrases and statistics related to quantitative assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idity
    -0.73
    phrine
    -0.64
    opal
    -0.58
    ãĤ¸
    -0.57
    perture
    -0.57
     secondly
    -0.54
    osure
    -0.54
     Awakens
    -0.54
    malink
    -0.53
    bour
    -0.52
    POSITIVE LOGITS
     upwards
    1.27
     tens
    1.24
     hundreds
    1.22
     anywhere
    1.16
     up
    1.15
     thousands
    1.13
     trillions
    1.09
     millions
    1.07
     billions
    1.06
     dozens
    1.01
    Activations Density 0.381%

    No Known Activations