© 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. 1-RES-JB
    11. 3635
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking action or being taken

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "taken" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lich
    -0.70
    hart
    -0.67
     Pupp
    -0.65
    til
    -0.63
    ler
    -0.63
    ihara
    -0.63
    eers
    -0.62
    hips
    -0.60
    nder
    -0.60
    Cong
    -0.60
    POSITIVE LOGITS
     aback
    1.13
     Taken
    0.96
    aways
    0.94
     Mehran
    0.84
    OVER
    0.81
    ardless
    0.80
     ACTIONS
    0.78
    ĸļ
    0.77
    ĭ
    0.76
     "$:/
    0.76
    Activations Density 0.022%

    No Known Activations