INDEX

Explanations

instances of the word "when."

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

 propOrder

-1.03

 purpoſe

-1.03

ArrowToggle

-1.02

 Normdatei

-1.00

 himſelf

-0.96

parsedMessage

-0.94

Personensuche

-0.92

 Jefus

-0.88

 houſe

-0.87

 bezeichneter

-0.87

POSITIVE LOGITS

 When

1.01

 when

0.97

When

0.93

 WHEN

0.91

when

0.91

 they

0.90

WHEN

0.88

we

0.83

Khi

0.81

 most

0.77

Activations Density 0.102%

instances of the word "when."

No Comments

No Known Activations