INDEX

Explanations

instances of trouble or problematic situations involving characters

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

Causing/getting into trouble

np_acts-logits-general · gemini-2.0-flash

causing trouble

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

EndContext

-0.60

 mangel

-0.51

řeba

-0.50

abancı

-0.49

pora

-0.49

assertNull

-0.49

TypedValue

-0.49

üksek

-0.49

itário

-0.48

pecia

-0.48

POSITIVE LOGITS

 trouble

2.08

 Trouble

1.73

trouble

1.72

Trouble

1.67

 troubles

1.42

 havoc

1.20

 bother

1.18

 mischief

1.17

 troublesome

1.16

 hassle

1.15

Activations Density 0.235%

instances of trouble or problematic situations involving characters

Causing/getting into trouble

causing trouble

No Comments

No Known Activations