INDEX

Explanations

terms related to workplace health and safety regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

sur

-0.53

addGap

-0.51

בות

-0.50

<eos>

-0.50

....

-0.50

im

-0.48

tra

-0.47

oney

-0.47

von

-0.46

 Datenschutz

-0.46

POSITIVE LOGITS

 Jefus

0.98

 itſelf

0.93

Efq

0.92

 myſelf

0.91

 Theſe

0.88

 becauſe

0.88

⦁

0.85

TagMode

0.85

ыгана

0.84

 leſs

0.83

Activations Density 0.212%

terms related to workplace health and safety regulations

No Comments

No Known Activations