INDEX

Explanations

phrases related to visual perception

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

-------

-0.62

CompleteListener

-0.60

CloseOperation

-0.55

ništvo

-0.54

IsContent

-0.53

basicConfig

-0.50

StoryboardSegue

-0.50

 faptul

-0.50

GenerationType

-0.49

mander

-0.49

POSITIVE LOGITS

 seeing

2.11

 sees

2.09

 seen

1.99

saw

1.97

see

1.91

seeing

1.90

 Seeing

1.79

 Sees

1.74

Seeing

1.73

 Seen

1.72

Activations Density 0.384%

phrases related to visual perception

No Comments

No Known Activations