INDEX

Explanations

references to ordinal numbers, particularly "fifth" and "sixth"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

er

-0.73

apos

-0.61

erai

-0.52

gdala

-0.52

ustris

-0.51

</i>

-0.51

HCR

-0.51

-0.50

-0.49

 transients

-0.49

POSITIVE LOGITS

 fifth

2.54

 sixth

2.47

 seventh

2.46

 fourth

2.39

fifth

2.35

 eighth

2.35

sixth

2.34

 ninth

2.32

Fifth

2.32

 Fifth

2.22

Activations Density 0.096%

references to ordinal numbers, particularly "fifth" and "sixth"

No Comments

No Known Activations