INDEX

Explanations

references to previous items or events

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

migrationBuilder

-0.83

)|^{

-0.79

học

-0.76

mobileqq

-0.73

 تضيفلها

-0.73

ValueStyle

-0.73

setVerticalGroup

-0.72

)++;

-0.72

 سكانية

-0.71

 mourut

-0.70

POSITIVE LOGITS

 previous

1.38

previous

1.31

 Previous

1.26

Previous

1.26

prev

1.09

 PREVIOUS

1.09

Prev

1.02

PREVIOUS

1.01

 предыду

1.00

 prev

0.98

Activations Density 0.439%

references to previous items or events

No Comments

No Known Activations