INDEX

Explanations

phrases and concepts related to interruptions and communication breakdowns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

});*/

-0.57

лерея

-0.56

GraphicsUnit

-0.56

rawDesc

-0.54

)++;

-0.53

 acquit

-0.51

*++

-0.51

 amas

-0.49

calloc

-0.49

StandardCharsets

-0.49

POSITIVE LOGITS

 interrupted

2.11

 interruption

2.08

 interrupt

2.02

 interrupting

1.91

 interruptions

1.81

 interrupts

1.78

interrupt

1.70

 Interrupt

1.68

 interrump

1.66

interrupted

1.66

Activations Density 0.365%

phrases and concepts related to interruptions and communication breakdowns

No Comments

No Known Activations