© 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. 10-RES-JB
    11. 17467
    Prev
    Next
    INDEX
    Explanations

    large numbers in a specific range

    oai_token-act-pair · gpt-3.5-turbo

    numerical data, particularly large figures related to populations or statistics

    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
    advant
    -0.73
    butt
    -0.61
     breeze
    -0.58
    inventoryQuantity
    -0.58
    eus
    -0.57
     AMERICA
    -0.56
    atorial
    -0.55
     Twist
    -0.53
    osit
    -0.52
     BET
    -0.52
    POSITIVE LOGITS
    %.
    1.16
     apiece
    1.12
    %,
    0.98
    +.
    0.89
     persons
    0.86
     individuals
    0.83
     tonnes
    0.81
     annually
    0.81
    *.
    0.81
     units
    0.81
    Activations Density 0.148%

    No Known Activations