INDEX

Explanations

phrases related to data collection and user feedback mechanisms

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

Expressing uncertainty or suggestions

np_acts-logits-general · gemini-2.0-flash

suggestions and possibilities

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

Almost

-0.86

almost

-0.80

 Almost

-0.76

 almost

-0.76

 почти

-0.72

 oftentimes

-0.69

Nearly

-0.69

 usually

-0.68

 nearly

-0.68

 bijna

-0.67

POSITIVE LOGITS

 maybe

1.23

 someday

1.14

 perhaps

1.13

maybe

1.06

perhaps

1.04

preferably

1.03

 preferably

1.02

 Maybe

1.01

 algún

0.98

 magari

0.95

Activations Density 1.053%

phrases related to data collection and user feedback mechanisms

Expressing uncertainty or suggestions

suggestions and possibilities

No Comments

No Known Activations