INDEX

Explanations

instances of declarations or statements made by the authors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

耿

-0.67

<strong>

-0.65

äksi

-0.61

isOk

-0.60

IContainer

-0.60

hop

-0.58

tim

-0.58

𝘅

-0.57

 Witt

-0.57

</em>

-0.56

POSITIVE LOGITS

 declaration

2.73

 declare

2.63

 declared

2.54

 declarations

2.53

 Declare

2.50

 declaring

2.41

 declares

2.39

 Declaration

2.38

declared

2.23

declaration

2.22

Activations Density 0.088%

instances of declarations or statements made by the authors

No Comments

No Known Activations