INDEX

Explanations

terms related to hiking and compilation processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

帖最后由

-0.55

 يتيمه

-0.50

ншни

-0.44

ngdoc

-0.41

AndEndTag

-0.41

oredCriteria

-0.41

exitRule

-0.40

⏟

-0.38

 незавершена

-0.38

 trend

-0.37

POSITIVE LOGITS

 hike

0.84

hike

0.70

 lodge

0.70

lodge

0.68

 Hike

0.66

ikes

0.63

 hiked

0.58

 Lodge

0.58

ike

0.57

 hikes

0.57

Activations Density 0.444%

terms related to hiking and compilation processes

No Comments

No Known Activations