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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 22266
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "self" or self-control

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "self" or self-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cill
    -0.73
    aldi
    -0.72
    cot
    -0.69
    lu
    -0.68
    cli
    -0.67
    cape
    -0.64
    lam
    -0.64
     mole
    -0.63
    gypt
    -0.62
    opers
    -0.61
    POSITIVE LOGITS
     Self
    3.35
     self
    1.63
    self
    1.56
    Self
    1.53
     selves
    1.20
     Mutual
    1.00
    selves
    0.98
     Personality
    0.98
     Narc
    0.96
     Subtle
    0.93
    Activations Density 0.005%

    No Known Activations