INDEX

Explanations

references to patients in a medical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 ſeveral

-1.19

Efq

-1.18

 itſelf

-1.17

 doubtnut

-1.16

 myſelf

-1.16

ſelves

-1.14

 ―――――

-1.12

 Theſe

-1.10

IntoConstraints

-1.10

 becauſe

-1.09

POSITIVE LOGITS

 patient

0.72

0.61

ction

0.58

0.57

 Patient

0.56

of

0.56

 type

0.56

 names

0.55

in

0.53

 named

0.53

Activations Density 0.234%

references to patients in a medical context

No Comments

No Known Activations