INDEX

Explanations

references to ratios or comparisons between quantities

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

runk

-0.62

Nec

-0.62

Will

-0.60

PEND

-0.59

moveToFirst

-0.59

‌

-0.58

 Го

-0.58

Buk

-0.58

oinette

-0.57

\\

-0.57

POSITIVE LOGITS

 ratio

2.38

 Ratio

2.33

 ratios

2.30

 RATIO

2.25

ratio

2.15

 Ratios

2.11

Ratio

2.06

ratios

1.88

RATIO

1.76

 ration

1.29

Activations Density 0.063%

references to ratios or comparisons between quantities

No Comments

No Known Activations