© 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. 1370
    Prev
    Next
    INDEX
    Explanations

    adjectives describing personality traits

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to personality traits and characteristics

    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
    osponsors
    -0.88
    Invalid
    -0.79
    qqa
    -0.77
    çīĪ
    -0.77
    govtrack
    -0.75
    SEA
    -0.74
    liga
    -0.73
    ctuary
    -0.73
    ievers
    -0.73
    ivably
    -0.72
    POSITIVE LOGITS
     demeanor
    1.63
     personality
    1.46
     attitude
    1.42
     disposition
    1.41
     temperament
    1.28
     tendencies
    1.27
     manner
    1.25
     persona
    1.24
     nature
    1.24
     charisma
    1.22
    Activations Density 0.167%

    No Known Activations