INDEX

Explanations

terms related to medical infections or illnesses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tagHelperRunner

-0.99

ngdoc

-0.74

 useEffect

-0.69

 дописавши

-0.69

 pinulongan

-0.65

 Hopf

-0.63

 Moslem

-0.63

},{

-0.63

קישורים

-0.63

 fotografico

-0.62

POSITIVE LOGITS

شناسی

0.50

цезда

0.49

fcntl

0.47

onnen

0.47

вики

0.46

 dato

0.45

municipi

0.45

tra

0.44

abinieri

0.43

âni

0.42

Activations Density 0.666%

terms related to medical infections or illnesses

No Comments

No Known Activations