INDEX

Explanations

references to messages or message-related concepts

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

"message"

np_acts-logits-general · gemini-2.0-flash

message and message type

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

 Wurzeln

-0.40

 curiosidad

-0.39

อยู่ใน

-0.39

 ferramentas

-0.38

ใช้

-0.38

 inoxidable

-0.37

 اختیار

-0.37

 freehold

-0.36

 estudar

-0.36

 incluindo

-0.36

POSITIVE LOGITS

 message

2.39

 Message

2.31

message

2.19

Message

2.09

 messages

2.09

 MESSAGE

2.00

 Messages

2.00

MESSAGE

1.82

 getMessage

1.79

Messages

1.75

Activations Density 0.084%

references to messages or message-related concepts

"message"

message and message type

No Comments

No Known Activations