INDEX

Explanations

negative prefixes such as "un-" indicating negation or reversal

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.39.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

 Sorensen

-0.44

ValueGenerated

-0.44

 propOrder

-0.35

 Detail

-0.34

plaatsen

-0.33

存在

-0.33

 höch

-0.33

 calientes

-0.33

 duração

-0.32

RenderAtEndOf

-0.32

POSITIVE LOGITS

viers

0.55

luck

0.54

icef

0.53

isons

0.53

 ſind

0.52

fortun

0.52

parsedMessage

0.51

GEBURTSDATUM

0.50

boxing

0.50

masking

0.49

Activations Density 0.187%

negative prefixes such as "un-" indicating negation or reversal

No Comments

No Known Activations