INDEX

Explanations

expressions related to teamwork and personal reflection

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

positive outcomes and actions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

تقاوى

-0.60

Varint

-0.57

NOPQRST

-0.52

 HttpHeaders

-0.51

+#+#

-0.49

 correctes

-0.49

 nameof

-0.48

遽

-0.48

">—

-0.48

ByKey

-0.47

POSITIVE LOGITS

 otomatig

0.73

 behaved

0.69

 enjoyed

0.67

 menikmati

0.67

做得

0.66

 thoroughly

0.64

 handled

0.64

AndEndTag

0.63

 fared

0.63

 enjoy

0.63

Activations Density 0.115%

expressions related to teamwork and personal reflection

positive outcomes and actions

No Known Activations