© 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. 3-RES-JB
    11. 23868
    Prev
    Next
    INDEX
    Explanations

    contractions of "is" with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    instances of the contraction "it's" indicating possession or state of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rating
    -0.61
    itcher
    -0.61
    IENT
    -0.60
    ={
    -0.60
    romancer
    -0.59
    velop
    -0.59
    arta
    -0.58
     Certain
    -0.58
    00000
    -0.57
    irm
    -0.56
    POSITIVE LOGITS
     gonna
    1.19
     gotta
    1.10
     been
    0.92
     got
    0.87
     worth
    0.83
    Ĥİ
    0.81
    been
    0.76
     not
    0.75
     supposed
    0.75
     going
    0.74
    Activations Density 0.104%

    No Known Activations