INDEX

Explanations

expressions of emotional responses, particularly negative feelings like disappointment, shock, and upset

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Xna

-0.83

 WaitForSeconds

-0.80

scrapy

-0.79

 tartalomajánló

-0.78

makeText

-0.78

 ExecuteAsync

-0.77

 transfieras

-0.77

idopsis

-0.76

webElementGuid

-0.76

 ddelweddau

-0.74

POSITIVE LOGITS

 surprised

0.76

 surpris

0.65

prised

0.65

surprised

0.64

 thinking

0.63

 pleased

0.61

 disappointed

0.61

 confident

0.60

 impressed

0.60

 disgusted

0.59

Activations Density 0.164%

expressions of emotional responses, particularly negative feelings like disappointment, shock, and upset

No Comments

No Known Activations