INDEX

Explanations

references to actions or effects related to physical interventions or medical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 nahilalakip

-0.78

<eos>

-0.71

 kaynağından

-0.71

ValueStyle

-0.68

تقاوى

-0.66

SpringBootTest

-0.66

awtextra

-0.66

 CreateTagHelper

-0.66

ResumeLayout

-0.63

AndEndTag

-0.61

POSITIVE LOGITS

 بيها

0.58

 Chriſt

0.56

CrossRef

0.55

版

0.53

MessageTagHelper

0.52

 fondation

0.52

octubre

0.52

ggere

0.51

</h2>

0.51

 يتيمه

0.50

Activations Density 0.591%

references to actions or effects related to physical interventions or medical conditions

No Comments

No Known Activations