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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14947
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of centering or focusing on a central point or activity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "cent," particularly in different contexts or phrases

    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
     ABE
    -0.73
     Tens
    -0.64
    ãģį
    -0.63
     Qiao
    -0.62
     Amos
    -0.61
     Kats
    -0.60
     Ake
    -0.59
     Ack
    -0.58
    IDES
    -0.58
     Jav
    -0.58
    POSITIVE LOGITS
    ennial
    1.71
    enary
    1.67
    uries
    1.56
    urion
    1.49
    imet
    1.42
    imeter
    1.38
    imeters
    1.28
    aur
    1.23
    ric
    1.21
    rals
    1.19
    Activations Density 0.042%

    No Known Activations