INDEX

Explanations

phrases related to the term "well-being"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 religieuses

-0.73

IUrlHelper

-0.64

 Roskov

-0.60

сылкі

-0.57

*~*~

-0.53

 lindas

-0.53

 industriel

-0.52

 rêver

-0.52

mitt

-0.52

atalos

-0.51

POSITIVE LOGITS

 versed

0.74

known

0.74

 known

0.72

springs

0.68

 WELL

0.66

 Well

0.66

 Welles

0.66

 wells

0.65

 suited

0.63

 worth

0.63

Activations Density 0.102%

phrases related to the term "well-being"

No Comments

No Known Activations