© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 13647
    Prev
    Next
    INDEX
    Explanations

    concepts related to the self and introspection

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the presence or absence of self-identity concepts

    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
    wat
    -0.82
    airo
    -0.81
     Constantine
    -0.77
    jah
    -0.75
    zen
    -0.75
    Corn
    -0.75
    ZX
    -0.74
    wich
    -0.74
     thunder
    -0.74
    Wars
    -0.73
    POSITIVE LOGITS
     Self
    2.21
     self
    2.05
    Self
    2.03
    self
    1.91
     selves
    1.57
    selves
    1.35
     autonomy
    1.34
     autonomous
    1.32
    ELF
    1.29
     autonom
    1.20
    Activations Density 0.213%

    No Known Activations