INDEX

Explanations

specialized terminology and definitions related to academic or scientific concepts

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

 suerte

-0.52

 сво

-0.49

-0.48

wnia

-0.45

 peau

-0.44

 sorte

-0.43

序

-0.40

adic

-0.40

 той

-0.40

 momentos

-0.40

POSITIVE LOGITS

SourceChecksum

1.03

MethodManager

0.94

InjectAttribute

0.91

tagHelperRunner

0.91

 كلمة

0.90

AndroidJUnit

0.86

 word

0.86

ScopeManager

0.86

ollectionView

0.84

rungsseite

0.82

Activations Density 0.269%

specialized terminology and definitions related to academic or scientific concepts

No Comments

No Known Activations