INDEX

Explanations

phrases indicating obligation or recommendation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

 mData

-0.86

 AssemblyCulture

-0.86

 alimentaires

-0.82

Efq

-0.82

PyExc

-0.80

 BoxDecoration

-0.78

 Jefus

-0.78

存于互联网档案馆

-0.75

 biografias

-0.75

DoubleQuotes

-0.75

POSITIVE LOGITS

 should

1.15

be

1.13

 SHOULD

1.07

hould

1.06

 Should

0.94

 could

0.90

 might

0.89

 have

0.88

 would

0.84

not

0.82

Activations Density 0.088%

phrases indicating obligation or recommendation

No Comments

No Known Activations