© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 22239
    Prev
    Next
    INDEX
    Explanations

    phrases related to oversight and control

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of supervision

    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
     outp
    -0.72
     Scythe
    -0.69
     Rush
    -0.69
    ifles
    -0.67
    cients
    -0.66
    ieft
    -0.66
    erker
    -0.66
     HRC
    -0.66
    itiveness
    -0.66
    egg
    -0.66
    POSITIVE LOGITS
     supervised
    3.46
     supervision
    2.51
     superv
    1.58
    vised
    1.39
     Sud
    1.28
     monitored
    1.17
     overseen
    1.15
    vard
    1.11
     curfew
    1.09
    lihood
    0.96
    Activations Density 0.051%

    No Known Activations