© 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. 9225
    Prev
    Next
    INDEX
    Explanations

    words related to a specific term or concept containing the subsequence "umb"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "umb" in words

    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
    SI
    -0.68
    creen
    -0.59
    Ò
    -0.58
     Chr
    -0.57
     chars
    -0.57
     Painter
    -0.54
     MON
    -0.53
     precon
    -0.53
     departure
    -0.53
    ctuary
    -0.53
    POSITIVE LOGITS
    rella
    1.16
    ucket
    1.07
    erer
    1.00
    ria
    0.99
    urg
    0.96
    lings
    0.96
    ayan
    0.94
    oku
    0.90
    erers
    0.89
    urger
    0.88
    Activations Density 0.051%

    No Known Activations