INDEX

Explanations

topics related to medical conditions and legal terminologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

SourceChecksum

-0.65

LookAnd

-0.62

fjspx

-0.60

ÍAS

-0.59

 noqa

-0.59

ÍN

-0.58

erta

-0.57

')(

-0.56

레이

-0.55

などなど

-0.54

POSITIVE LOGITS

 only

0.74

 because

0.63

 hany

0.58

 потому

0.57

 uniquement

0.57

 únicamente

0.57

 änd

0.56

 without

0.55

 hanya

0.53

ArrowToggle

0.51

Activations Density 1.477%

topics related to medical conditions and legal terminologies

No Comments

No Known Activations