INDEX

Explanations

instances of the word "then" indicating a sequence of events or conclusions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Harlow

-0.82

 himſelf

-0.82

 ejus

-0.79

 Bär

-0.79

Efq

-0.78

 ftate

-0.76

 Winfrey

-0.76

 Cæsar

-0.75

 purpoſe

-0.74

 Folsom

-0.74

POSITIVE LOGITS

 THEN

1.28

 Then

1.22

 then

1.18

THEN

1.16

Then

1.12

then

1.01

 Dann

0.99

Dann

0.96

dann

0.92

 Luego

0.90

Activations Density 0.184%

instances of the word "then" indicating a sequence of events or conclusions

No Comments

No Known Activations