INDEX

Explanations

references to lakes and wetland ecosystems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ulemon

-0.54

IBarButtonItem

-0.54

Distribución

-0.54

taminophen

-0.52

hysema

-0.52

 Printable

-0.52

estinal

-0.52

 Meksiku

-0.51

thansa

-0.49

limsy

-0.49

POSITIVE LOGITS

 lake

0.81

 pond

0.70

 pool

0.66

 lakes

0.66

 Lake

0.60

 ponds

0.59

 pools

0.57

 basin

0.56

Lake

0.54

lake

0.51

Activations Density 0.363%

references to lakes and wetland ecosystems

No Comments

No Known Activations