Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 21190
    Prev
    Next
    INDEX
    Explanations

    words related to characteristics, traits, and behaviors of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of personality

    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
     Safe
    -0.70
    bare
    -0.68
    ews
    -0.66
    safe
    -0.65
    fully
    -0.65
    ¶
    -0.65
    saf
    -0.64
    WARE
    -0.64
     Supported
    -0.64
    \.
    -0.64
    POSITIVE LOGITS
     personality
    3.79
     personalities
    2.98
     Personality
    2.82
     temperament
    1.83
     persona
    1.77
     charisma
    1.66
     individuality
    1.60
     demeanor
    1.37
     ego
    1.30
     narciss
    1.30
    Activations Density 0.027%

    No Known Activations