INDEX

Explanations

terms related to medical diagnoses and treatments, particularly those associated with psychological conditions and dosage administration

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

skjaer

-0.68

RectangleBorder

-0.56

gely

-0.56

 Rivière

-0.54

ituary

-0.52

styleType

-0.49

 losses

-0.49

 Blume

-0.49

躇

-0.48

bye

-0.48

POSITIVE LOGITS

 annual

0.79

 monthly

0.75

 weekly

0.75

 daily

0.72

 yearly

0.71

 quarterly

0.68

annual

0.67

 еже

0.65

 QName

0.64

 annually

0.64

Activations Density 1.573%

terms related to medical diagnoses and treatments, particularly those associated with psychological conditions and dosage administration

No Comments

No Known Activations