© 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. 0-RES-JB
    11. 10415
    Prev
    Next
    INDEX
    Explanations

    references to the term "IS" with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the term "IS" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rag
    -0.66
     Zup
    -0.66
    uffle
    -0.62
    ample
    -0.62
    ocamp
    -0.61
    Cu
    -0.60
    ackle
    -0.59
     caffe
    -0.58
    ulhu
    -0.58
     Gord
    -0.57
    POSITIVE LOGITS
     IS
    3.62
    IS
    1.99
     HAS
    1.68
     DOES
    1.50
     ARE
    1.44
     WAS
    1.44
     RIS
    1.43
     IF
    1.39
     IST
    1.38
     AS
    1.36
    Activations Density 0.012%

    No Known Activations