© 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. 2-RES-JB
    11. 467
    Prev
    Next
    INDEX
    Explanations

    the word "networks"

    oai_token-act-pair · gpt-4-turbo

    references to technological networks, specifically emphasizing publicly accessible Wi-Fi networks

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various types of networks, particularly in technology contexts

    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
    onement
    -0.62
    ×Ķ
    -0.62
     Boy
    -0.61
     Nordic
    -0.61
     Continental
    -0.59
    âķIJâķIJ
    -0.58
     Falk
    -0.58
    Synopsis
    -0.57
    Honest
    -0.56
    anan
    -0.56
    POSITIVE LOGITS
    mith
    1.26
    ystem
    1.24
    cape
    1.17
    wana
    1.16
    etting
    1.16
    pace
    1.14
    hips
    1.11
    hops
    1.11
    chool
    1.11
    paces
    1.10
    Activations Density 0.045%

    No Known Activations