INDEX

Explanations

specific patterns or sequences in numerical data or formatted strings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Nine

-1.47

-1.45

 nine

-1.39

 ninth

-1.25

 Ninth

-1.25

 ninety

-1.17

 NINE

-1.14

 Ninety

-1.13

Nine

-1.12

 nueve

-1.10

POSITIVE LOGITS

twimg

0.61

addContainerGap

0.57

 nahilalakip

0.57

 ModelExpression

0.57

 vijf

0.56

SIX

0.54

0.53

Obrázky

0.52

四

0.52

Activations Density 0.597%

specific patterns or sequences in numerical data or formatted strings

No Comments

No Known Activations