© 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. 6-RES-JB
    11. 22662
    Prev
    Next
    INDEX
    Explanations

    mentions or references to specific titles or positions, such as "Officer" or "bystander"

    oai_token-act-pair · gpt-3.5-turbo

    references to law enforcement and related personnel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VM
    -0.70
    nikov
    -0.70
     logger
    -0.67
     potatoes
    -0.63
    BALL
    -0.62
     fertility
    -0.61
     terrestrial
    -0.60
     breathing
    -0.59
     fertil
    -0.57
     metab
    -0.57
    POSITIVE LOGITS
    er
    1.08
    ues
    1.05
    uing
    1.03
    emate
    0.94
    uers
    0.93
    ued
    0.91
    omen
    0.86
    IAL
    0.86
    ials
    0.85
    ements
    0.84
    Activations Density 0.075%

    No Known Activations