INDEX

Explanations

references to the concept of "year."

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

}")

-0.62

":"",

-0.60

 later

-0.60

 senere

-0.59

ormais

-0.58

depuis

-0.56

 earlier

-0.53

 позже

-0.53

 ostavi

-0.52

waypoints

-0.51

POSITIVE LOGITS

 Paglinawan

0.90

 layui

0.69

 Boven

0.67

 виправивши

0.66

Tazama

0.66

 оригіналу

0.65

rogels

0.63

 thiệu

0.61

lapia

0.60

tvguidetime

0.60

Activations Density 0.071%

references to the concept of "year."

No Comments

No Known Activations