INDEX

Explanations

words related to choices, decisions, and taking action, with some activation also for anatomical terms

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 grafting

-0.61

 grafted

-0.52

 Kens

-0.49

 sogni

-0.48

 Dosis

-0.47

 sessile

-0.46

rody

-0.44

 rebuild

-0.43

Card

-0.43

 umbro

-0.43

POSITIVE LOGITS

DeleteBehavior

0.81

 للمعارف

0.72

:+:

0.72

ReusableCell

0.70

 propOrder

0.69

tvguidetime

0.68

 CreateTagHelper

0.67

 <<<<<<<<<<<<<<

0.66

libft

0.65

 numberWith

0.65

Activations Density 46.889%

words related to choices, decisions, and taking action, with some activation also for anatomical terms

No Comments

No Known Activations