INDEX

Explanations

temporal references related to time, especially words indicating lateness or subsequent events

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

ammen

-0.50

 dieß

-0.49

 McCle

-0.49

IContainer

-0.48

 ſind

-0.47

,:);

-0.47

googleapis

-0.42

 nothwendig

-0.42

%)$

-0.41

Morrison

-0.41

POSITIVE LOGITS

 LATE

0.94

 Late

0.94

Late

0.89

 late

0.86

late

0.83

LATE

0.79

later

0.67

lastTime

0.65

 LATER

0.63

 Later

0.61

Activations Density 0.103%

temporal references related to time, especially words indicating lateness or subsequent events

No Comments

No Known Activations