© 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. 17199
    Prev
    Next
    INDEX
    Explanations

    hyperlinks or related text indicating the presence of links within a document

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "links" in various forms

    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
    Merit
    -0.84
    IRE
    -0.80
    sburg
    -0.76
    otos
    -0.75
    ARS
    -0.71
    ority
    -0.65
    Ħ¢
    -0.64
     Penguins
    -0.64
    ZI
    -0.63
    oÄŁ
    -0.63
    POSITIVE LOGITS
     links
    1.22
     Links
    1.04
    edin
    0.98
    links
    0.95
     linking
    0.94
    cius
    0.93
     link
    0.90
    link
    0.90
    Links
    0.86
    lash
    0.85
    Activations Density 0.012%

    No Known Activations