INDEX

Explanations

numeric values and statistical results

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

 tartalomajánló

-0.75

andowski

-0.58

eynman

-0.53

 елның

-0.53

GEBURTS

-0.52

ftagPool

-0.49

idopsis

-0.48

Földrajzportál

-0.48

льки

-0.48

 Waray

-0.47

POSITIVE LOGITS

 quæ

0.88

 pleaſure

0.77

 ejus

0.74

ſelf

0.74

ſy

0.72

UnusedPrivate

0.71

 myſelf

0.68

 convertView

0.67

 uſed

0.66

 houſe

0.66

Activations Density 0.226%

numeric values and statistical results

No Comments

No Known Activations