INDEX

Explanations

references to programming and technical implementations

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

 normalidad

-0.47

<eos>

-0.46

стат

-0.46

-0.43

’

-0.41

↵↵

-0.41

…

-0.41

стати

-0.40

 ochran

-0.39

”

-0.39

POSITIVE LOGITS

 بيها

0.91

ThroughAttribute

0.88

setVerticalGroup

0.87

MLLoader

0.83

+#+#

0.81

 виправивши

0.78

Hauptartikel

0.78

tagHelperRunner

0.77

abestanden

0.77

 myſelf

0.76

Activations Density 0.879%

references to programming and technical implementations

No Comments

No Known Activations