© 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. 1457
    Prev
    Next
    INDEX
    Explanations

    negative character traits and actions

    oai_token-act-pair · gpt-3.5-turbo

    character traits and behaviors of individuals

    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
    çīĪ
    -0.77
    DragonMagazine
    -0.76
    rolet
    -0.71
    ucc
    -0.71
    EMBER
    -0.70
    PDATED
    -0.67
    named
    -0.67
    omsky
    -0.66
     GOODMAN
    -0.66
    elman
    -0.65
    POSITIVE LOGITS
     chores
    1.05
     subordinates
    1.03
     enthus
    0.94
     himself
    0.88
     mischief
    0.87
     routines
    0.85
     things
    0.84
     teammates
    0.83
     hobbies
    0.83
     bullies
    0.83
    Activations Density 0.657%

    No Known Activations