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

    Neuronpedia

    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. 1241
    Prev
    Next
    INDEX
    Explanations

    numbers or quantities mentioned in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical data and statistics related to populations and scientific variables

    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
    cffffcc
    -0.99
    ãĤ´ãĥ³
    -0.75
    lace
    -0.75
     Relations
    -0.72
     srfAttach
    -0.70
     guise
    -0.68
    çīĪ
    -0.64
    ascript
    -0.64
    ebin
    -0.64
    RAW
    -0.64
    POSITIVE LOGITS
     per
    1.08
     counted
    1.06
     consumed
    1.00
     allowed
    0.92
     permitted
    0.91
     polled
    0.91
     surveyed
    0.90
     allocated
    0.90
     admitted
    0.90
     allotted
    0.88
    Activations Density 0.257%

    No Known Activations