© 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. 2-RES-JB
    11. 21213
    Prev
    Next
    INDEX
    Explanations

    phrases related to the processing and use of paste, especially in the context of food or materials

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "paste" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    axies
    -0.77
    izons
    -0.71
     perpend
    -0.65
     bells
    -0.65
    rians
    -0.65
     Gry
    -0.64
    hips
    -0.64
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.61
    vae
    -0.61
     Democr
    -0.60
    POSITIVE LOGITS
    urized
    1.41
     paste
    1.26
    ur
    1.01
    lete
    0.94
     Paste
    0.91
    paste
    0.90
    ebin
    0.82
    uring
    0.78
    aste
    0.77
    ocol
    0.76
    Activations Density 0.008%

    No Known Activations