INDEX

Explanations

phrases indicating dates or numerical sequences

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

 årene

-0.59

iastes

-0.58

 Jahrgang

-0.52

 Hamlet

-0.50

Years

-0.49

Hamlet

-0.49

انگلیسی

-0.48

iksa

-0.47

 comerciais

-0.46

 Shakspeare

-0.45

POSITIVE LOGITS

LEncoder

0.74

脚注の使い方

0.70

 mergeFrom

0.68

Autoritní

0.67

 tanggal

0.67

WaitGroup

0.62

 Gleaner

0.61

fromLTRB

0.60

 typelib

0.59

Diweddarwch

0.59

Activations Density 0.140%

phrases indicating dates or numerical sequences

No Comments

No Known Activations