INDEX

Explanations

occurrences of the word "caught" and related actions indicating detection or observation

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 تحص

-0.61

bly

-0.55

bye

-0.55

 GenerationType

-0.55

Wra

-0.54

+":

-0.53

jdt

-0.53

 Rost

-0.52

osene

-0.51

"}")

-0.51

POSITIVE LOGITS

 discovered

1.71

 detected

1.60

 spotted

1.59

 noticed

1.46

discovered

1.44

 Discovered

1.42

 Detected

1.37

 encountered

1.33

 observed

1.26

 Spotted

1.22

Activations Density 0.255%

occurrences of the word "caught" and related actions indicating detection or observation

No Comments

No Known Activations