INDEX

Explanations

dates and temporal references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 GetEnumerator

-0.72

AddAttribute

-0.63

 Kass

-0.61

lawayo

-0.61

 Jennings

-0.61

makeText

-0.60

holde

-0.59

msgSender

-0.59

edance

-0.59

JsonNode

-0.56

POSITIVE LOGITS

 April

2.12

April

1.95

 APRIL

1.80

APRIL

1.69

 april

1.68

 avril

1.50

 abril

1.48

april

1.45

 aprile

1.44

 Abril

1.27

Activations Density 0.068%

dates and temporal references

No Comments

No Known Activations