INDEX

Explanations

phrases indicating possession or relationships involving "of."

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

is

-0.84

was

-0.69

an

-0.59

 témoins

-0.58

ion

-0.56

 attentes

-0.55

su

-0.54

 does

-0.53

 itself

-0.51

er

-0.51

POSITIVE LOGITS

 '\\;'

1.02

ſelves

0.95

 cherchés

0.92

 }}$}

0.92

adaptiveStyles

0.90

."</

0.87

"])

0.86

)";

0.85

✨:

0.83

 CURIAM

0.83

Activations Density 0.628%

phrases indicating possession or relationships involving "of."

No Comments

No Known Activations