INDEX

Explanations

phrases indicating disclaimers or cautionary advice regarding medical content and professional recommendations

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

PyExc

-0.55

 Wikimedijinoj

-0.47

lodash

-0.46

]++;

-0.45

цезда

-0.44

cknow

-0.43

 cortas

-0.43

tikai

-0.43

RLock

-0.43

#+#

-0.42

POSITIVE LOGITS

RepeatedField

0.71

SupportActionBar

0.69

 contained

0.64

SpringBootTest

0.64

 contents

0.56

 initComponents

0.55

Begriffsklä

0.55

ElementException

0.55

contained

0.54

 nahilalakip

0.53

Activations Density 1.049%

phrases indicating disclaimers or cautionary advice regarding medical content and professional recommendations

No Comments

No Known Activations