© 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. 7-RES-JB
    11. 2229
    Prev
    Next
    INDEX
    Explanations

    individuals and their titles in professional settings

    oai_token-act-pair · gpt-3.5-turbo

    titles and roles within organizations, particularly executive positions

    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
     queen
    -0.79
     reper
    -0.77
     needle
    -0.72
     contag
    -0.72
     peril
    -0.71
     queens
    -0.71
    toggle
    -0.70
     bite
    -0.70
     destro
    -0.69
     overwhelm
    -0.68
    POSITIVE LOGITS
     Candidate
    1.20
     Manager
    1.16
     Coordinator
    1.12
     Officer
    1.09
     Relations
    1.06
     Leader
    1.04
     Ambassador
    1.04
     Emer
    1.03
     Content
    1.03
     Accountability
    1.02
    Activations Density 0.139%

    No Known Activations