INDEX

Explanations

terms associated with medical and biological concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

вини

-0.47

 ADVENT

-0.45

kalender

-0.45

 anticip

-0.43

 træ

-0.43

setForm

-0.43

ույ

-0.42

 campaign

-0.42

tri

-0.42

lampa

-0.42

POSITIVE LOGITS

MigrationBuilder

1.03

findpost

1.01

 مرئيه

0.93

ⓧ

0.92

 protoimpl

0.91

NewGuid

0.90

Становништво

0.88

 '\\;'

0.88

 estekak

0.88

SourceChecksum

0.87

Activations Density 1.033%

terms associated with medical and biological concepts

No Comments

No Known Activations