INDEX

Explanations

medical terminology and associations related to health risks and treatments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

ItemLayout

-0.65

 losses

-0.54

 Losses

-0.52

miary

-0.52

 losing

-0.48

 Châ

-0.48

 становника

-0.48

PhysRev

-0.47

ząt

-0.47

 guiding

-0.47

POSITIVE LOGITS

 cause

0.94

 causes

0.86

cause

0.81

Cause

0.79

 Cause

0.77

 CAUSE

0.76

 trigger

0.76

causes

0.74

 causing

0.71

 provoque

0.70

Activations Density 0.280%

medical terminology and associations related to health risks and treatments

No Comments

No Known Activations