INDEX

Explanations

references to boards or decision-making groups

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

yntaxException

-0.92

__).

-0.77

iTunes

-0.76

InstanceState

-0.74

)++;

-0.73

Hef

-0.73

pernic

-0.73

Zeneca

-0.71

}>;

-0.70

NameInMap

-0.70

POSITIVE LOGITS

 board

3.97

board

3.76

 boards

3.54

 Board

3.47

Board

3.44

boards

3.33

 BOARD

3.26

BOARD

3.17

 Boards

3.12

Boards

2.81

Activations Density 0.048%

references to boards or decision-making groups

No Comments

No Known Activations