INDEX

Explanations

patterns in numerical data, particularly related to formatting and structure

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

hasMoreElements

-0.56

vertreter

-0.53

Specifier

-0.52

Wal

-0.48

 فق

-0.48

فض

-0.48

andri

-0.47

 الشم

-0.47

elemField

-0.45

ftagPool

-0.45

POSITIVE LOGITS

migrationBuilder

0.75

 insuffisamment

0.72

basicConfig

0.69

المكان

0.68

 становника

0.66

 BoxFit

0.65

 EconPapers

0.63

minyak

0.63

withIdentifier

0.61

Дереккөздер

0.61

Activations Density 0.033%

patterns in numerical data, particularly related to formatting and structure

No Comments

No Known Activations