INDEX

Explanations

structured lists or sequences of ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

 oprot

-0.69

verwijspagina

-0.64

expandindo

-0.62

$}}

-0.61

BagLayout

-0.61

 pinulongan

-0.60

MethodManager

-0.60

 NDEBUG

-0.60

providedIn

-0.60

ArrowToggle

-0.58

POSITIVE LOGITS

 اینکه

0.68

 Secondly

0.59

 importantly

0.58

 secondly

0.58

 nữa

0.58

 thing

0.56

 belangrijk

0.56

 important

0.55

volves

0.55

 Thirdly

0.55

Activations Density 0.284%

structured lists or sequences of ideas

No Comments

No Known Activations