INDEX

Explanations

phrases that indicate the presence of conditions or criteria that are typically followed in structured discussions or analyses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

]-->

-0.73

 onCreateView

-0.73

 فريبيس

-0.73

]")]

-0.62

__))

-0.60

 Roskov

-0.59

.*")]

-0.58

PerformLayout

-0.57

 endwhile

-0.55

MLLoader

-0.54

POSITIVE LOGITS

 Waray

0.67

 يتيمه

0.66

 Arki

0.63

styleUrls

0.62

Cof

0.61

 Reſ

0.60

 nahilalakip

0.59

DebuggerStep

0.58

Спољашње

0.58

 Algunos

0.57

Activations Density 0.461%

phrases that indicate the presence of conditions or criteria that are typically followed in structured discussions or analyses

No Comments

No Known Activations