INDEX

Explanations

indicators of the start or end of sections or blocks of text

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 دیکھیے

-0.63

 transvers

-0.60

 Italijani

-0.58

 binomial

-0.58

 Numerade

-0.57

pushFollow

-0.56

 gradova

-0.55

 liné

-0.54

EDEFAULT

-0.53

 Secondo

-0.53

POSITIVE LOGITS

 IBOutlet

0.79

 Réponses

0.61

 protoimpl

0.60

 الاطلاع

0.58

 Chwiliwch

0.58

 hinaus

0.55

createCanvas

0.54

IANGLES

0.54

 Paglinawan

0.54

FunctionFlags

0.54

Activations Density 0.289%

indicators of the start or end of sections or blocks of text

No Comments

No Known Activations