INDEX

Explanations

terms related to bar charts and their components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 متعلقه

-1.21

.)}

-0.92

--}}

-0.88

>")

-0.86

');?>

-0.86

")}

-0.84

iented

-0.83

Aktualisiert

-0.83

 beginnetje

-0.82

__':

-0.80

POSITIVE LOGITS

bar

1.51

BAR

1.50

bar

1.49

BAR

1.47

 bars

1.45

Bar

1.44

Bar

1.42

Bars

1.33

 Bars

1.29

bars

1.23

Activations Density 0.096%

terms related to bar charts and their components

No Comments

No Known Activations