INDEX

Explanations

terms related to "corruption" and its effects or implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Houſe

-0.96

########.

-0.92

 Anſ

-0.86

★☆

-0.85

mybatisplus

-0.85

 faſt

-0.85

 uſe

-0.84

).\\

-0.84

 Theſe

-0.82

 ſta

-0.81

POSITIVE LOGITS

Cor

1.61

COR

1.60

Cor

1.48

cor

1.46

COR

1.39

cor

1.33

 Corbett

1.33

 Correa

1.29

 Corcoran

1.24

 Corbin

1.22

Activations Density 0.101%

terms related to "corruption" and its effects or implications

No Comments

No Known Activations