© 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. 9094
    Prev
    Next
    INDEX
    Explanations

    pronouns indicating personal or possessive belongings

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and expressions of hard work

    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
    viron
    -0.75
    hyde
    -0.72
     Lerner
    -0.68
    ixel
    -0.68
    ð
    -0.64
    cephal
    -0.59
    PLA
    -0.58
    cker
    -0.58
     Vide
    -0.57
    _-
    -0.57
    POSITIVE LOGITS
     own
    0.97
     way
    0.93
     asses
    0.88
     entire
    0.84
     dues
    0.84
     damned
    0.83
     hardest
    0.81
     whole
    0.81
     hearts
    0.80
     conscience
    0.78
    Activations Density 0.072%

    No Known Activations