© 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. 11422
    Prev
    Next
    INDEX
    Explanations

    personal opinions or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    first-person and third-person pronouns indicating subjective opinions and personal perspectives

    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
     beware
    -0.67
     Concern
    -0.65
    quartered
    -0.63
    unction
    -0.61
     ineligible
    -0.61
     Dragonbound
    -0.60
    aware
    -0.59
    bol
    -0.59
     doubtful
    -0.57
    ORY
    -0.56
    POSITIVE LOGITS
     preached
    0.99
     accomplished
    0.96
     wrought
    0.86
     done
    0.81
     presented
    0.77
     wrote
    0.75
     posted
    0.75
     achieved
    0.74
     narrated
    0.74
     accomplish
    0.73
    Activations Density 0.155%

    No Known Activations