© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 11080
    Prev
    Next
    INDEX
    Explanations

    terms related to administrative actions, such as "administrative leave" and "administrative nightmare"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "administrative" in relation to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âķIJâķIJ
    -0.94
    eem
    -0.92
    hov
    -0.88
    ï¸
    -0.84
    ku
    -0.79
    xual
    -0.77
    sung
    -0.76
    ooth
    -0.74
    acus
    -0.73
    lings
    -0.72
    POSITIVE LOGITS
     procedures
    0.89
     tasks
    0.89
    rative
    0.88
     instit
    0.88
     assistant
    0.81
     substitution
    0.81
     administrative
    0.81
     subpoen
    0.81
     hurdles
    0.79
     oversight
    0.79
    Activations Density 0.031%

    No Known Activations