INDEX

Explanations

discussions of disasters or significant negative events

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

 JpaRepository

-0.57

atrième

-0.51

antung

-0.48

amos

-0.48

 SearchView

-0.48

ütz

-0.47

 Tired

-0.47

 tired

-0.47

 Debate

-0.46

)’

-0.45

POSITIVE LOGITS

 happening

1.45

 happen

1.38

 occurrence

1.37

 happened

1.35

 events

1.34

happen

1.27

 Happen

1.22

 occurring

1.21

 occur

1.20

 event

1.19

Activations Density 0.373%

discussions of disasters or significant negative events

No Comments

No Known Activations