INDEX

Explanations

emphasized or descriptive modifiers that enhance the intensity of statements

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

parsedMessage

-0.59

ubmit

-0.58

 svolta

-0.57

antaranya

-0.55

šli

-0.51

خرى

-0.50

zeitig

-0.48

 tearDown

-0.48

CROSSTALK

-0.47

 życie

-0.47

POSITIVE LOGITS

 nakalista

0.73

 autorytatywna

0.69

 consultato

0.67

تقاوى

0.67

 propOrder

0.65

loroethene

0.63

ThroughAttribute

0.63

 >=",

0.62

<",

0.62

EndGlobalSection

0.59

Activations Density 0.349%

emphasized or descriptive modifiers that enhance the intensity of statements

No Comments

No Known Activations