INDEX

Explanations

elements related to health and medical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_mlp_out

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

 noses

-0.66

 BorderRadius

-0.65

 nose

-0.59

 implies

-0.57

HomeAsUpEnabled

-0.55

itiv

-0.54

glicher

-0.53

 pleaſure

-0.53

 conventional

-0.52

 copro

-0.52

POSITIVE LOGITS

出版年

0.71

IsContent

0.60

secutions

0.54

igshid

0.54

photobucket

0.53

findpost

0.52

.*")]

0.52

Autoritní

0.52

expandindo

0.50

Demografia

0.50

Activations Density 1.231%

elements related to health and medical conditions

No Comments

No Known Activations