INDEX

Explanations

numerical values and counts in the text

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

 chevalier

-0.71

Efq

-0.63

hésite

-0.62

Ainda

-0.62

Tikang

-0.62

 Romains

-0.61

 mourut

-0.61

colage

-0.61

 superiori

-0.61

 magie

-0.61

POSITIVE LOGITS

two

0.96

 four

0.86

 three

0.86

two

0.81

 major

0.81

 zwei

0.79

zwei

0.77

 два

0.75

new

0.74

 five

0.74

Activations Density 0.657%

numerical values and counts in the text

No Comments

No Known Activations