INDEX

Explanations

references to various locations or places

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

 referenties

-0.63

RenderAtEndOf

-0.58

SourceChecksum

-0.54

χος

-0.54

 aste

-0.53

 MwSt

-0.53

MigrationBuilder

-0.52

 piedi

-0.52

artiges

-0.52

 protoimpl

-0.51

POSITIVE LOGITS

 places

2.79

 Places

2.55

 PLACES

2.42

Places

2.40

places

2.30

 lugares

1.61

 locations

1.59

 spots

1.58

 endroits

1.37

 steder

1.34

Activations Density 0.105%

references to various locations or places

No Comments

No Known Activations