INDEX

Explanations

words indicating time and temporal contexts in situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 läßt

-1.32

 muß

-1.25

 idéia

-1.21

 daß

-1.20

 skall

-1.11

 mußte

-1.09

 Einfluß

-1.02

 Schluß

-1.01

luß

-0.94

 müßte

-0.93

POSITIVE LOGITS

⁠

1.23

 Notably

1.12

 demnach

1.04

1.03

 incentiv

1.00

0.99

0.96

Alongside

0.96

 onboarding

0.96

️

0.92

Activations Density 0.436%

words indicating time and temporal contexts in situations

No Comments

No Known Activations