INDEX

Explanations

the presence of specific tokens frequently used in programming syntax or documentation

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

Followed by prepositions or conjunctions

np_acts-logits-general · gemini-2.0-flash

context for clauses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 itſelf

-0.59

ſelf

-0.49

 Houſe

-0.49

 Portail

-0.48

 Pergamon

-0.47

 damska

-0.46

 houſe

-0.45

ſelves

-0.45

bodyParser

-0.45

forgettable

-0.45

POSITIVE LOGITS

 there

1.43

 they

1.18

it

1.06

there

1.04

we

1.00

 THERE

0.86

 nobody

0.85

he

0.83

 although

0.80

 There

0.79

Activations Density 0.141%

the presence of specific tokens frequently used in programming syntax or documentation

Followed by prepositions or conjunctions

context for clauses

No Comments

No Known Activations