INDEX

Explanations

comparative phrases indicating a lesser quantity

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

less than

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 įva

-0.52

 podró

-0.52

 solches

-0.51

 alimentação

-0.49

 alimentación

-0.48

 Hinblick

-0.48

 použí

-0.47

 gyóg

-0.46

Зноскі

-0.46

 transición

-0.46

POSITIVE LOGITS

LessThan

0.69

 Less

0.69

Under

0.66

 Under

0.65

 less

0.63

Less

0.62

 LESS

0.61

}<

0.58

 under

0.56

 UNDER

0.56

Activations Density 0.009%

comparative phrases indicating a lesser quantity

less than

No Comments

No Known Activations