INDEX

Explanations

instances of specific phrases or terms indicating case studies or examples

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

StoryboardSegue

-0.86

 henvisninger

-0.69

 ThemeData

-0.67

Hozzáférés

-0.67

 AttributeSet

-0.66

UrlResolution

-0.66

Cyfeiriadau

-0.66

Hilsen

-0.62

ittarius

-0.61

thora

-0.59

POSITIVE LOGITS

 particular

0.60

 diesmal

0.57

DockStyle

0.57

SourceChecksum

0.55

landse

0.55

 case

0.52

openqa

0.51

uk

0.48

 specifico

0.48

 particolare

0.47

Activations Density 0.281%

instances of specific phrases or terms indicating case studies or examples

No Comments

No Known Activations