INDEX

Explanations

occurrences of the word "new" and its variations in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/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.21.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

 Winaray

-0.60

 propOrder

-0.59

UrlResolution

-0.57

ceptre

-0.54

 viewDidLoad

-0.52

operatorname

-0.52

 courseId

-0.51

ISME

-0.50

lieder

-0.49

 onFailure

-0.49

POSITIVE LOGITS

new

1.22

new

1.15

New

1.11

New

1.05

NEW

1.04

NEW

0.93

 Nuevas

0.90

 neuen

0.85

新

0.82

 nieuwe

0.82

Activations Density 0.128%

occurrences of the word "new" and its variations in context

No Comments

No Known Activations