INDEX

Explanations

commands or directives

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

NewUrlParser

-0.73

 bezeichneter

-0.72

httphttps

-0.71

losures

-0.67

',)

-0.66

pira

-0.66

})*/

-0.63

 RSSSF

-0.63

')")

-0.63

herself

-0.63

POSITIVE LOGITS

 HasFactory

0.49

 argent

0.47

 mecan

0.46

xnn

0.44

onAttach

0.42

RAID

0.41

passing

0.40

ɟ

0.40

āciju

0.40

 thous

0.40

Activations Density 0.122%

commands or directives

No Comments

No Known Activations