INDEX

Explanations

phrases that indicate actions or processes associated with orders and instructions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Jefus

-1.46

 pleaſure

-1.44

Efq

-1.40

 houſe

-1.39

 Monfieur

-1.37

 myſelf

-1.36

 Majefty

-1.33

 Theſe

-1.32

 faſt

-1.32

 themſelves

-1.30

POSITIVE LOGITS

 afin

0.88

 inorder

0.83

 أجل

0.81

 чтобы

0.77

是为了

0.74

to

0.73

 upang

0.71

kében

0.70

Чтобы

0.70

 כדי

0.70

Activations Density 0.071%

phrases that indicate actions or processes associated with orders and instructions

No Comments

No Known Activations