INDEX

Explanations

technical and scientific terms related to electronic and display technologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

AxisAlignment

-0.57

Hochspringen

-0.56

DOCTYPE

-0.50

*}[

-0.50

:"-"`

-0.48

 ioutil

-0.48

BeginInit

-0.47

AND

-0.47

Revenir

-0.46

日在

-0.46

POSITIVE LOGITS

HasBeenSet

0.73

tanleria

0.65

windowFixed

0.65

ArrowToggle

0.60

 intStringLen

0.60

Autoritní

0.58

queryInterface

0.56

 Numerade

0.56

 wikipagina

0.55

 préfé

0.55

Activations Density 0.411%

technical and scientific terms related to electronic and display technologies

No Comments

No Known Activations