INDEX

Explanations

questions related to processes and comparisons in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

cu

-0.57

жен

-0.55

bari

-0.53

Unsigned

-0.51

entrySet

-0.51

picasso

-0.51

 крае

-0.50

 fournir

-0.49

 There

-0.49

POSITIVE LOGITS

how

1.37

 कैसे

1.15

 ways

1.12

HOW

1.10

How

1.05

Kako

1.05

יצד

1.05

Hvordan

1.05

 Nasıl

1.03

 cómo

1.03

Activations Density 0.252%

questions related to processes and comparisons in various contexts

No Comments

No Known Activations