INDEX

Explanations

references to carbon monoxide (CO) in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AlterField

-0.75

unknownFields

-0.67

 صوتيه

-0.66

таратура

-0.63

 Apoll

-0.61

itez

-0.60

pollo

-0.59

tonsoft

-0.59

tlv

-0.58

DotNetBar

-0.56

POSITIVE LOGITS

CO

1.49

CO

1.30

 monoxide

1.02

SCO

0.92

ftagPool

0.91

VO

0.88

"><?=

0.87

VO

0.83

 createSprite

0.82

SO

0.82

Activations Density 0.086%

references to carbon monoxide (CO) in various contexts

No Comments

No Known Activations