INDEX

Explanations

phrases and concepts related to questioning and evaluating medical theories or treatments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

зулта

-0.51

ban

-0.50

########.

-0.48

ini

-0.46

hung

-0.45

ote

-0.44

ulti

-0.44

der

-0.44

ater

-0.41

ast

-0.41

POSITIVE LOGITS

 ddelweddau

0.80

StoreMessageInfo

0.76

✨:

0.69

äsident

0.68

iastes

0.67

issauga

0.66

 للاسماء

0.66

 '\\;'

0.65

fromnode

0.64

principalColumn

0.63

Activations Density 1.303%

phrases and concepts related to questioning and evaluating medical theories or treatments

No Comments

No Known Activations