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

    Neuronpedia

    Jacobian LensNEW
    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. 1997
    Prev
    Next
    INDEX
    Explanations

    mentions of military or security personnel

    oai_token-act-pair · gpt-3.5-turbo

    references to personnel across various contexts

    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
    sat
    -0.76
    ken
    -0.70
    sweet
    -0.68
    joy
    -0.67
    dx
    -0.66
    fest
    -0.66
     Roots
    -0.65
    ether
    -0.64
    weet
    -0.62
     Drawing
    -0.62
    POSITIVE LOGITS
     personnel
    3.60
     Personnel
    2.77
     manpower
    1.66
     staffing
    1.58
     staff
    1.58
     technicians
    1.45
     employees
    1.44
     staffers
    1.38
     crews
    1.29
     operatives
    1.23
    Activations Density 0.013%

    No Known Activations