INDEX

Explanations

adjectives and related forms indicating challenges or complexities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

omány

-0.68

up

-0.68

 jugé

-0.66

laps

-0.63

ar

-0.63

 cherchez

-0.61

che

-0.61

ings

-0.59

thru

-0.58

hold

-0.58

POSITIVE LOGITS

ficulties

0.97

BibitemShut

0.97

 myſelf

0.96

MENAFN

0.95

 opport

0.92

StoryboardSegue

0.91

Viki

0.91

uſ

0.91

 ――――――――

0.90

 Difficulties

0.90

Activations Density 0.052%

adjectives and related forms indicating challenges or complexities

No Comments

No Known Activations