INDEX

Explanations

conjunctions and expressions indicating connections between ideas

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

immediately after "and"

np_acts-logits-general · gemini-2.0-flash

conjunction or subsequent action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Houſe

-0.60

carbonyl

-0.56

rawDesc

-0.56

 carbonyl

-0.52

nack

-0.52

CppMethod

-0.51

 uLocal

-0.50

 Majefty

-0.49

 itemName

-0.49

ſt

-0.49

POSITIVE LOGITS

hygiène

0.55

to

0.54

 Grüsse

0.51

 démocratie

0.48

 transición

0.47

 Verhältnisse

0.46

 puissiez

0.46

 build

0.45

 evolve

0.45

 quieras

0.45

Activations Density 0.390%

conjunctions and expressions indicating connections between ideas

immediately after "and"

conjunction or subsequent action

No Comments

No Known Activations