INDEX

Explanations

concepts related to recommendations and assessments in the context of behavior change interventions

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

 Réponses

-0.66

RegressionTest

-0.65

ViewFeatures

-0.65

 unknownFields

-0.64

parsedMessage

-0.61

enterOuterAlt

-0.60

 ivelany

-0.57

 مواليد

-0.57

expandindo

-0.56

 пожалуйста

-0.55

POSITIVE LOGITS

 prompted

0.84

 certainly

0.83

 notwithstanding

0.78

 shouldn

0.77

 culminated

0.72

 seems

0.70

 comes

0.69

certainly

0.68

 continues

0.64

 surfaced

0.63

Activations Density 0.590%

concepts related to recommendations and assessments in the context of behavior change interventions

No Comments

No Known Activations