INDEX

Explanations

references to quantities or amounts in various contexts

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

amount of

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

iſchen

-0.67

 borbo

-0.58

inspector

-0.56

 cerah

-0.56

ỡng

-0.56

Rüyada

-0.56

 scegliere

-0.55

SqlDataReader

-0.55

 pizarra

-0.55

 [''],

-0.54

POSITIVE LOGITS

 amount

1.22

Amount

1.15

 Amount

1.12

 amounts

1.09

amount

1.05

 AMOUNT

0.96

 Amounts

0.94

Amounts

0.91

AMOUNT

0.90

amounts

0.82

Activations Density 0.013%

references to quantities or amounts in various contexts

amount of

No Comments

No Known Activations

references to quantities or amounts in various contexts

amount of

No Comments

No Known Activations