INDEX

Explanations

titles or references to medical professionals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

downe

-0.66

 Leaven

-0.63

gulier

-0.62

 Mosaic

-0.60

ranean

-0.58

tones

-0.58

ements

-0.54

 Harden

-0.54

 Lino

-0.54

 Comet

-0.53

POSITIVE LOGITS

Dr

1.74

Dr

1.64

dr

1.13

Drs

1.10

Mrs

1.02

Mr

1.01

 docteur

1.00

 डॉ

0.94

Mrs

0.93

 Docteur

0.90

Activations Density 0.178%

titles or references to medical professionals

No Comments

No Known Activations