INDEX

Explanations

numeric values and codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

出版年

-0.63

MENAFN

-0.63

BeginContext

-0.61

 المعيارى

-0.60

 labels

-0.59

 Labels

-0.59

 Truth

-0.58

 truth

-0.58

 TRUTH

-0.57

UIControlState

-0.56

POSITIVE LOGITS

الدراسه

0.47

 AppComponent

0.47

AddTagHelper

0.44

 base

0.44

asmuch

0.44

reportWebVitals

0.43

曖昧さ回避

0.43

 disambiguazione

0.42

 Compass

0.42

umably

0.41

Activations Density 0.464%

numeric values and codes

No Comments

No Known Activations