INDEX

Explanations

references to learning and teaching across various contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

nodoc

-0.65

kman

-0.53

urlopen

-0.52

httphttps

-0.49

jspx

-0.49

 bút

-0.49

ImageField

-0.48

shank

-0.47

 pris

-0.47

PACS

-0.47

POSITIVE LOGITS

learning

1.44

 learning

1.41

learned

1.40

 taught

1.40

 Taught

1.37

 learns

1.37

learn

1.36

 learnt

1.36

 learn

1.35

 learned

1.34

Activations Density 0.195%

references to learning and teaching across various contexts

No Known Activations