© 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. 9-RES-JB
    11. 20747
    Prev
    Next
    INDEX
    Explanations

    the word "this" associated with other terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "this" and similar demonstrative pronouns indicating specific references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.95
    BuyableInstoreAndOnline
    -0.78
    thood
    -0.77
    zac
    -0.70
    othy
    -0.68
    gage
    -0.68
    igger
    -0.67
    Í
    -0.66
    ZE
    -0.66
    ~~~~
    -0.66
    POSITIVE LOGITS
     consequ
    1.18
     resultant
    1.14
     accordingly
    1.11
     consequently
    1.09
     ensuing
    0.99
     accompanying
    0.97
     subsequent
    0.95
     resulting
    0.92
     proceeds
    0.89
     results
    0.89
    Activations Density 0.376%

    No Known Activations