INDEX

Explanations

the word "over" and its various usages in sentences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

expandindo

-0.72

chism

-0.61

 unknownFields

-0.59

marginVertical

-0.56

casian

-0.55

riwal

-0.53

kijken

-0.53

ayanan

-0.52

 wensen

-0.52

djangoproject

-0.51

POSITIVE LOGITS

lords

0.79

lord

0.77

tures

0.76

whelming

0.67

 yonder

0.66

igens

0.66

ture

0.65

 Overs

0.65

 OVER

0.64

heads

0.64

Activations Density 0.165%

the word "over" and its various usages in sentences

No Comments

No Known Activations