INDEX

Explanations

occurrences of variations of the word "OT" and its contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.36.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

TemporalType

-0.68

 pinulongan

-0.67

UnusedPrivate

-0.65

новништво

-0.60

PreExecute

-0.59

MemoryWarning

-0.57

bolista

-0.57

horse

-0.57

رشف

-0.55

queryInterface

-0.55

POSITIVE LOGITS

ter

0.47

Kot

0.45

ton

0.42

ted

0.41

TER

0.40

ting

0.40

ters

0.40

Cot

0.40

Kot

0.39

ot

0.38

Activations Density 0.274%

occurrences of variations of the word "OT" and its contexts

No Comments

No Known Activations