© 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. 7-RES-JB
    11. 23034
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "te"

    oai_token-act-pair · gpt-3.5-turbo

    the word "te" and its variations used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interrupted
    -0.72
    ipolar
    -0.69
    OST
    -0.69
    lessly
    -0.65
     bottleneck
    -0.64
     obligated
    -0.61
    etheless
    -0.61
    antha
    -0.61
    istically
    -0.60
    usher
    -0.60
    POSITIVE LOGITS
    brate
    1.44
    brates
    1.36
    ller
    1.19
    llers
    1.14
    levision
    1.10
    achers
    1.08
    llo
    1.06
    achable
    1.05
    aching
    1.01
    lla
    0.97
    Activations Density 0.027%

    No Known Activations