INDEX

Explanations

instances that indicate conditions for success or effective outcomes

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

 resourceCulture

-0.85

AsUp

-0.83

parsedMessage

-0.81

expandindo

-0.76

 referenties

-0.75

 myſelf

-0.74

 ―――――

-0.74

 SwitchCompat

-0.72

 itſelf

-0.72

 moschino

-0.71

POSITIVE LOGITS

can

0.66

 then

0.66

 shouldn

0.64

may

0.64

 should

0.61

you

0.58

it

0.56

 will

0.55

 thì

0.54

do

0.54

Activations Density 0.250%

instances that indicate conditions for success or effective outcomes

No Comments

No Known Activations