INDEX

Explanations

numerical data related to measurements or observations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

okovic

-0.69

 nakalista

-0.64

 GetEnumerator

-0.63

Efq

-0.62

ellido

-0.62

makeConstraints

-0.62

Véxase

-0.61

úgó

-0.60

참고

-0.59

Hentet

-0.59

POSITIVE LOGITS

SharedCtor

0.67

 طريق

0.57

IsMutable

0.54

SourceChecksum

0.52

 Bere

0.51

 betweenstory

0.51

-.

0.47

rony

0.47

läs

0.47

Activations Density 0.454%

numerical data related to measurements or observations

No Comments

No Known Activations