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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 23624
    Prev
    Next
    INDEX
    Explanations

    phrases related to social interactions and psychological characteristics, such as emotional intelligence, sensitivity, and interpersonal skills

    oai_token-act-pair · gpt-3.5-turbo

    instances of statements related to psychological traits or social dynamics

    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
     satell
    -1.00
    ascus
    -0.94
     landfall
    -0.90
     nomine
    -0.88
     gobl
    -0.86
     earthqu
    -0.86
     millenn
    -0.85
    emort
    -0.80
    alore
    -0.78
     feasible
    -0.78
    POSITIVE LOGITS
     Conversely
    1.40
     Often
    1.37
     Researchers
    1.28
     Sometimes
    1.25
     Psychological
    1.24
     Individuals
    1.21
     Likewise
    1.20
     Saying
    1.19
     Knowing
    1.19
     Understanding
    1.19
    Activations Density 0.460%

    No Known Activations