INDEX

Explanations

words related to medical conditions 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 @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 theaters

-1.15

 disks

-1.07

 viață

-1.05

 theater

-1.04

 gages

-1.03

Theater

-1.01

 Ее

-1.00

 Theaters

-0.99

 Stearns

-0.99

 parlor

-0.98

POSITIVE LOGITS

 licences

1.30

 metres

1.28

 moulds

1.27

 Colours

1.23

 artefacts

1.19

 enquiries

1.15

 fibres

1.15

Colours

1.15

 Enquiries

1.14

 favourites

1.13

Activations Density 5.913%

words related to medical conditions and treatments

No Comments

No Known Activations