INDEX

Explanations

words related to health interventions and outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

@"/

-0.58

 CanadaChoose

-0.57

Примечания

-0.49

">)</

-0.49

Ma

-0.49

co

-0.48

piel

-0.48

blad

-0.47

|}\

-0.47

pro

-0.47

POSITIVE LOGITS

 myſelf

0.73

 itſelf

0.72

ostante

0.71

цездатний

0.69

RuleContext

0.67

 uſed

0.66

 Shakspeare

0.65

 Seleccione

0.65

 оригіналу

0.63

 IFTTT

0.62

Activations Density 1.592%

words related to health interventions and outcomes

No Comments

No Known Activations