© 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. 10-RES-JB
    11. 11257
    Prev
    Next
    INDEX
    Explanations

    terms related to policies and positions in organizational structures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to leadership roles and policy-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pload
    -0.88
     whiff
    -0.69
    soDeliveryDate
    -0.66
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.65
    \/\/
    -0.64
    False
    -0.63
     Lantern
    -0.63
    nee
    -0.62
    Ü
    -0.61
     captcha
    -0.60
    POSITIVE LOGITS
     affairs
    0.94
     Affairs
    0.86
     sciences
    0.82
     Operations
    0.81
     Programs
    0.80
     operations
    0.78
    ometry
    0.77
     communications
    0.76
     consulting
    0.75
     studies
    0.73
    Activations Density 0.114%

    No Known Activations