INDEX

Explanations

names of individuals and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

SpringRunner

-0.67

 الحره

-0.57

gog

-0.54

åne

-0.53

+#+#

-0.53

hynch

-0.52

alip

-0.51

็จ

-0.51

liament

-0.51

SPEAKER

-0.51

POSITIVE LOGITS

 Brothers

0.90

 Family

0.81

 brothers

0.77

 family

0.75

Autoritní

0.75

 BROTHERS

0.74

 Bros

0.73

brothers

0.72

family

0.72

Brothers

0.71

Activations Density 0.714%

names of individuals and entities

No Comments

No Known Activations