INDEX

Explanations

technical and regulatory terms related to scientific and medical contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-1.27

↵

-0.59

nicity

-0.54

↵↵

-0.53

“

-0.51

rój

-0.50

 Paglinawan

-0.50

"}"

-0.49

cted

-0.48

ppings

-0.47

POSITIVE LOGITS

 UITableView

0.76

WebVitals

0.73

ISupport

0.70

XtraEditors

0.69

 ContentValues

0.69

ollectionView

0.67

CodedInputStream

0.67

 ComVisible

0.67

 gainera

0.65

 GeoNames

0.64

Activations Density 2.080%

technical and regulatory terms related to scientific and medical contexts

No Comments

No Known Activations