INDEX

Explanations

phrases that indicate deception or manipulation regarding historical narratives or beliefs

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

Being tricked, fooled, or deceived

np_acts-logits-general · gemini-2.0-flash

falling for deception

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.30.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

rrggbb

-0.46

usercontent

-0.43

httphttps

-0.41

ียญ

-0.38

MockMvc

-0.37

 belangrij

-0.37

UAGES

-0.36

ніципа

-0.36

 displeasure

-0.36

twimg

-0.36

POSITIVE LOGITS

 naive

1.23

gul

1.17

 fooled

1.16

 naïve

1.11

 naï

1.05

 unsuspecting

1.01

 foolish

0.99

 fool

0.93

 deceived

0.91

naive

0.90

Activations Density 0.396%

phrases that indicate deception or manipulation regarding historical narratives or beliefs

Being tricked, fooled, or deceived

falling for deception

No Comments

No Known Activations