INDEX

Explanations

words indicating regrets and accountability for actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

ようになります

-0.55

Existing

-0.48

logg

-0.46

ებ

-0.45

ようになる

-0.43

marle

-0.43

chitz

-0.42

phus

-0.41

 indisponible

-0.41

decade

-0.41

POSITIVE LOGITS

 yesterday

1.16

 kemarin

1.11

yesterday

1.05

Yesterday

0.99

 вчера

0.97

 Yesterday

0.96

 tadi

0.94

 ontem

0.93

 earlier

0.91

earlier

0.82

Activations Density 0.422%

words indicating regrets and accountability for actions

No Comments

No Known Activations