© 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. 5485
    Prev
    Next
    INDEX
    Explanations

    phrases related to someone or something being taken somewhere

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "taken."

    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
    lich
    -0.72
    ullah
    -0.68
    eers
    -0.66
    witz
    -0.64
    Cong
    -0.63
    ler
    -0.62
    nder
    -0.62
     embr
    -0.60
     Pupp
    -0.59
    psey
    -0.59
    POSITIVE LOGITS
     aback
    1.11
    aways
    0.97
    OVER
    0.89
    ãĤ¤ãĥĪ
    0.86
     ACTIONS
    0.84
    ãĥĥãĥĪ
    0.84
     Taken
    0.82
     Mehran
    0.78
    ĭ
    0.75
    arnaev
    0.75
    Activations Density 0.040%

    No Known Activations