INDEX

Explanations

phrases related to time and objects involved in events

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

time and specific durations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

Not in Any Lists

No Comments

Negative Logits

-0.81

ième

-0.47

stanbul

-0.47

ohjel

-0.47

 onPause

-0.46

 kérd

-0.45

Ведь

-0.45

still

-0.44

zerű

-0.44

sver

-0.43

POSITIVE LOGITS

<bos>

0.90

𝓵

0.74

𝓲

0.67

𝓮

0.66

𝓭

0.65

𝓴

0.65

𝓫

0.62

𝓯

0.61

 Ader

0.60

ン

0.60

Activations Density 0.034%

phrases related to time and objects involved in events

time and specific durations

No Comments

No Known Activations