INDEX

Explanations

words related to medical terminology and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 porosity

-0.50

 vertes

-0.47

υγ

-0.45

کز

-0.41

 dominions

-0.41

COMMON

-0.41

common

-0.40

[++

-0.39

izando

-0.39

 common

-0.39

POSITIVE LOGITS

ValueStyle

0.55

IsMutable

0.54

zation

0.53

llo

0.51

gnore

0.50

mple

0.50

brium

0.49

yah

0.49

 EconPapers

0.49

llos

0.49

Activations Density 0.218%

words related to medical terminology and conditions

No Comments

No Known Activations