INDEX

Explanations

details about medical conditions and emergency responses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 autorytatywna

-0.66

acimiento

-0.56

expiresIn

-0.56

awtextra

-0.56

tempted

-0.48

 These

-0.48

LastError

-0.47

 memin

-0.46

ynb

-0.46

ancourt

-0.46

POSITIVE LOGITS

 suddenly

0.60

 Tragedy

0.59

 soudain

0.57

createClass

0.57

 abruptly

0.57

 melaporkan

0.56

suddenly

0.56

 alerted

0.56

esez

0.55

 commotion

0.54

Activations Density 0.255%

details about medical conditions and emergency responses

No Comments

No Known Activations