INDEX

Explanations

references to academic institutions or organizations

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

setVerticalGroup

-0.90

yntaxException

-0.87

Tē

-0.75

 PyLong

-0.69

TypedDataSet

-0.65

AndEndTag

-0.65

osoba

-0.65

ьаж

-0.65

ReusableCell

-0.63

ifflin

-0.62

POSITIVE LOGITS

באנגלית

0.47

 esterni

0.46

 دیکھیے

0.44

ungalows

0.43

<bos>

0.42

Coordenadas

0.41

newArrayList

0.41

 dõi

0.41

 estratégica

0.41

География

0.41

Activations Density 0.793%

references to academic institutions or organizations

No Comments

No Known Activations