INDEX

Explanations

structures and organization within data formats, particularly involving nested or hierarchical arrangements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

ل

-0.62

 Lovato

-0.60

com

-0.60

Sil

-0.60

 Oates

-0.59

Kand

-0.58

◄

-0.58

nos

-0.57

Com

-0.56

 Loeb

-0.55

POSITIVE LOGITS

 referenties

0.90

EndContext

0.89

 Czechoslovakia

0.86

 Charlemagne

0.84

 useAppContext

0.82

 Spaniard

0.81

 Redwood

0.80

 nakalista

0.80

 <<<<<<<<<<<<<<

0.80

 Credo

0.79

Activations Density 0.154%

structures and organization within data formats, particularly involving nested or hierarchical arrangements

No Comments

No Known Activations