© 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. 9902
    Prev
    Next
    INDEX
    Explanations

    words related to currencies

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ron" and its variations

    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
    tub
    -0.71
    RED
    -0.68
    urai
    -0.67
     Norn
    -0.66
    mable
    -0.64
    Redd
    -0.62
    URA
    -0.61
    geries
    -0.59
    arers
    -0.58
    gery
    -0.57
    POSITIVE LOGITS
    auts
    1.25
    autical
    1.07
    omical
    1.05
    aldo
    1.04
     Collider
    1.01
    uclear
    1.00
    omy
    0.99
    stadt
    0.98
    omics
    0.93
    etary
    0.91
    Activations Density 0.054%

    No Known Activations