INDEX

Explanations

phrases contrasting different concepts or ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 purpoſe

-0.67

 themſelves

-0.63

 leſs

-0.60

 reaſon

-0.60

 JTable

-0.59

 Monfieur

-0.59

 Majefty

-0.58

 Magist

-0.58

 ſte

-0.57

 susun

-0.57

POSITIVE LOGITS

 whereas

1.30

Whereas

1.23

whereas

1.21

 Whereas

1.17

 sedangkan

1.05

Sedangkan

1.04

 Sedangkan

1.00

 dagegen

0.97

 meanwhile

0.96

 while

0.91

Activations Density 0.216%

phrases contrasting different concepts or ideas

No Comments

No Known Activations