INDEX

Explanations

words related to pharmaceutical products 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-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_mlp_out

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

 تانيه

-0.68

 فريبيس

-0.68

 simplifié

-0.66

 BoxFit

-0.63

 चीज़ों

-0.63

日閲覧

-0.62

WireFormat

-0.60

 intptr

-0.59

[]:

-0.58

انجليز

-0.58

POSITIVE LOGITS

 Slick

0.52

 "{\"

0.47

 Parcelable

0.47

 better

0.47

loxy

0.45

 निय

0.44

palm

0.44

 pytest

0.44

openConnection

0.43

 leps

0.43

Activations Density 0.871%

words related to pharmaceutical products and treatments

No Comments

No Known Activations