INDEX

Explanations

references to specific medical cases and patient populations

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

tvguidetime

-0.63

 Evol

-0.56

essoal

-0.55

onuclear

-0.54

ições

-0.53

ValueGeneration

-0.52

 arrogance

-0.51

 Immort

-0.49

 revolved

-0.49

äsent

-0.49

POSITIVE LOGITS

 suffering

1.62

 suffer

1.57

 suffers

1.52

 Suffering

1.31

suffering

1.22

 Suffer

1.22

 suffered

1.19

 sufrir

1.03

 souff

0.97

 experiencing

0.95

Activations Density 0.626%

references to specific medical cases and patient populations

No Comments

No Known Activations