INDEX

Explanations

instances of the word "bad," particularly in negative contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 EconPapers

-0.53

 protoimpl

-0.49

 avoient

-0.47

parsedMessage

-0.47

NameInMap

-0.46

 Leuten

-0.45

 navideña

-0.45

 romántica

-0.45

XmlAccessorType

-0.45

 arşivlendi

-0.44

POSITIVE LOGITS

bad

0.80

bad

0.76

Bad

0.56

BAD

0.56

Bad

0.52

BAD

0.51

abad

0.50

 Smith

0.50

 mission

0.50

pack

0.49

Activations Density 0.268%

instances of the word "bad," particularly in negative contexts

No Comments

No Known Activations