INDEX

Explanations

references to programming structures or components, particularly in code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 hivyo

-0.54

ophora

-0.52

Ẽ

-0.52

 Lehmann

-0.51

 cataly

-0.51

öbb

-0.50

以上

-0.49

 total

-0.49

//

-0.49

POSITIVE LOGITS

 CreateTagHelper

0.79

]")]

0.77

contentLoaded

0.72

AddTagHelper

0.69

下载附件

0.66

archiviato

0.66

tagHelperRunner

0.66

GEBURTS

0.65

IsContent

0.61

出版年

0.60

Activations Density 0.015%

references to programming structures or components, particularly in code snippets

No Comments

No Known Activations