INDEX

Explanations

patterns or structures in formatted data

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 AssemblyVersion

-0.72

Mat

-0.67

Ke

-0.65

Fig

-0.62

McK

-0.60

etwork

-0.59

 Nishi

-0.59

}[!

-0.57

bür

-0.57

vocable

-0.56

POSITIVE LOGITS

 ----------

1.37

 -------

1.35

 ------

1.32

----------

1.32

------

1.27

-------

1.24

--------

1.23

 --------

1.22

 ---------

1.22

-----

1.13

Activations Density 0.269%

patterns or structures in formatted data

No Comments

No Known Activations