INDEX

Explanations

formatting cues or structural elements in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

Przypisy

-0.53

Defect

-0.48

gridx

-0.48

cences

-0.46

 needs

-0.46

 Needs

-0.45

fır

-0.45

 Asset

-0.45

 Perspective

-0.45

ScrollView

-0.44

POSITIVE LOGITS

CJK

1.11

CJK

0.75

 snippetHide

0.69

+#+#

0.67

ejs

0.62

 jadx

0.61

")){

0.60

aarrggbb

0.60

RetentionPolicy

0.59

:+:

0.58

Activations Density 0.019%

formatting cues or structural elements in text

No Comments

No Known Activations