INDEX

Explanations

references to specific scientific entities, including terms related to genetics and microbiology

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Tokens following the word "the"

np_acts-logits-general · gemini-2.0-flash

the + common words

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 letter

-0.51

 thing

-0.51

 little

-0.50

bit

-0.49

way

-0.48

 beautiful

-0.48

ẠI

-0.48

ੱ

-0.47

thought

-0.47

 istore

-0.47

POSITIVE LOGITS

 estekak

0.85

ագրություններ

0.78

Portail

0.75

 للمعارف

0.74

)];

0.73

GEBURTSDATUM

0.72

 betweenstory

0.71

RepeatedField

0.70

InitVars

0.68

oredCriteria

0.67

Activations Density 1.557%

references to specific scientific entities, including terms related to genetics and microbiology

Tokens following the word "the"

the + common words

No Comments

No Known Activations