INDEX

Explanations

terms related to results and their validation in scientific research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

et

-0.58

↵↵

-0.55

-0.53

to

-0.53

is

-0.52

-0.51

the

-0.51

ver

-0.51

-0.50

POSITIVE LOGITS

 myſelf

1.26

 itſelf

1.17

 Jefus

1.16

 purpoſe

1.09

 ་་

1.08

$_"

1.07

 ―――――

1.07

 ſeveral

1.07

 Monfieur

1.07

 Theſe

1.04

Activations Density 0.425%

terms related to results and their validation in scientific research

No Comments

No Known Activations