INDEX

Explanations

sections marked by significant formatting or structure changes, likely indicating distinct passages or important transitions in the 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

baomidou

-0.54

יתה

-0.52

 aéri

-0.52

RunAsync

-0.51

 faisons

-0.50

TagMode

-0.49

idade

-0.49

amese

-0.48

verat

-0.46

AGEM

-0.44

POSITIVE LOGITS

tvguidetime

0.72

onViewCreated

0.66

=$?

0.65

tableFuture

0.65

Hentet

0.65

 {}));

0.63

Бележки

0.61

KommentareTeilen

0.59

 autorytatywna

0.58

sidemargin

0.58

Activations Density 0.062%

sections marked by significant formatting or structure changes, likely indicating distinct passages or important transitions in the text

No Comments

No Known Activations