INDEX

Explanations

comparative phrases and expressions

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

 ſeveral

-1.31

 myſelf

-1.25

 purpoſe

-1.19

 pleaſure

-1.17

 Majefty

-1.16

 fubject

-1.11

 ſtate

-1.07

 faſt

-1.07

 itſelf

-1.06

 ſever

-1.05

POSITIVE LOGITS

 than

1.09

than

0.81

 THAN

0.74

 compared

0.71

 Than

0.68

 daripada

0.62

 dibandingkan

0.61

Than

0.61

Compared

0.60

 decât

0.60

Activations Density 0.332%

comparative phrases and expressions

No Comments

No Known Activations