INDEX

Explanations

personal names and references to individuals

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للاسماء

-0.66

AutoresizingMask

-0.65

 getItemId

-0.63

 dasarnya

-0.62

UPI

-0.60

่านั้น

-0.58

astify

-0.57

expandindo

-0.56

onOptions

-0.56

berdayakan

-0.55

POSITIVE LOGITS

TagMode

0.68

 interview

0.60

 interviews

0.58

 interviewer

0.54

 interviewing

0.53

interview

0.52

 चीज़ों

0.51

ElementException

0.51

 interviewed

0.49

 interviewers

0.48

Activations Density 0.212%

personal names and references to individuals

No Comments

No Known Activations