INDEX

Explanations

references to specific conditions or observations that necessitate further investigation or consideration

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

like "seem", "appear", or "looks"

np_acts-logits-general · gemini-2.0-flash

seems or appears

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

abestanden

-0.76

 '\\;'

-0.74

ValueStyle

-0.73

 avulla

-0.68

 متعلقه

-0.68

IntoConstraints

-0.65

MessageOf

-0.64

Personendaten

-0.63

 disambiguazione

-0.63

rawDesc

-0.63

POSITIVE LOGITS

 seems

2.81

 seem

2.67

 appears

2.44

seems

2.35

 seemed

2.28

 appear

2.26

 Seems

2.20

seem

2.14

Seems

2.13

 semble

2.01

Activations Density 0.533%

references to specific conditions or observations that necessitate further investigation or consideration

like "seem", "appear", or "looks"

seems or appears

No Comments

No Known Activations

references to specific conditions or observations that necessitate further investigation or consideration

like "seem", "appear", or "looks"

seems or appears

No Comments

No Known Activations