INDEX

Explanations

conditional phrases and statements about consequences or situations that imply uncertainty or variability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

InjectAttribute

-0.81

arraycopy

-0.54

setVerticalGroup

-0.53

 glyphicon

-0.48

TestFixture

-0.47

andid

-0.45

Zaj

-0.44

setCharacter

-0.42

 Useful

-0.40

babu

-0.40

POSITIVE LOGITS

 समीक्षाओं

0.72

 kasarigan

0.71

]`

0.69

μία

0.66

niająca

0.64

évaluateur

0.63

 Mitteln

0.62

mistry

0.62

 gärna

0.61

 StringField

0.60

Activations Density 0.151%

conditional phrases and statements about consequences or situations that imply uncertainty or variability

No Comments

No Known Activations