© 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. 0-RES-JB
    11. 7626
    Prev
    Next
    INDEX
    Explanations

    words related to managing or control

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "managed."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erence
    -0.69
    plates
    -0.63
    auga
    -0.62
    abe
    -0.61
    âĻ¦
    -0.61
     recip
    -0.61
     accus
    -0.60
     passage
    -0.60
    endo
    -0.60
    ativity
    -0.60
    POSITIVE LOGITS
     managed
    3.54
     manages
    2.30
    managed
    2.24
     manage
    2.13
     managing
    1.55
     maintained
    1.51
     succeeded
    1.42
     survived
    1.34
     handled
    1.27
     achieved
    1.27
    Activations Density 0.015%

    No Known Activations