INDEX

Explanations

references to numerical values or specifications, particularly in a technical or programming context

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

RenderAtEndOf

-0.85

OrNil

-0.83

Portail

-0.83

########.

-0.82

MemoryWarning

-0.81

 Савезне

-0.80

PerformLayout

-0.80

 CreateTagHelper

-0.79

Datuak

-0.77

 виправивши

-0.76

POSITIVE LOGITS

 Harris

0.47

 Austin

0.46

 global

0.43

AYA

0.43

contentLoaded

0.43

";

0.42

";

0.42

 tous

0.41

</h5>

0.40

Activations Density 0.792%

references to numerical values or specifications, particularly in a technical or programming context

No Comments

No Known Activations