INDEX

Explanations

phrases indicating requests for additional information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

parsedMessage

-0.58

InSection

-0.52

ftagPool

-0.50

wußt

-0.48

 HasFactory

-0.48

styleType

-0.47



-0.45

󠁣

-0.43

 вікісторінку

-0.42

cheinend

-0.42

POSITIVE LOGITS

 more

0.98

 information

0.97

 further

0.94

 inquiries

0.81

 details

0.80

 info

0.76

 enquiries

0.75

information

0.73

 informasi

0.72

further

0.71

Activations Density 0.144%

phrases indicating requests for additional information

No Comments

No Known Activations