INDEX

Explanations

references to actions and observations involving the concept of "looking" or examining

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

ReusableCell

-0.61

 незавершена

-0.59

Predecesor

-0.58

 فريبيس

-0.58

 kaynağından

-0.56

]--;

-0.54

 дописавши

-0.53

 GenerationType

-0.53

NameInMap

-0.52

łku

-0.51

POSITIVE LOGITS

at

3.63

at

1.87

At

1.83

At

1.82

 tại

1.81

AT

1.16

1.15

ở

1.11

atx

1.03

Tại

1.03

Activations Density 4.708%

references to actions and observations involving the concept of "looking" or examining

No Comments

No Known Activations