© 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. 11-RES-JB
    11. 6730
    Prev
    Next
    INDEX
    Explanations

    mentions of past associations or relationships, particularly related to employment or personal connections

    oai_token-act-pair · gpt-3.5-turbo

    references to past relationships and positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ovember
    -0.78
     themselves
    -0.70
    Die
    -0.69
    cius
    -0.69
    ARCH
    -0.68
    abbage
    -0.67
    -+-+
    -0.66
     yourselves
    -0.66
    otle
    -0.66
    zanne
    -0.64
    POSITIVE LOGITS
     employer
    1.38
     employers
    1.17
     haun
    1.15
     adversary
    1.06
     surroundings
    1.06
     roommate
    1.05
     girlfriend
    1.05
     selves
    1.04
     mentor
    1.03
     foe
    1.03
    Activations Density 0.129%

    No Known Activations