INDEX

Explanations

references to temporal concepts and life events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 arrivo

-0.73

 choose

-0.70

 assume

-0.68

 expect

-0.68

explique

-0.67

be

-0.67

 ensure

-0.66

 decide

-0.65

 conclude

-0.64

 learn

-0.64

POSITIVE LOGITS

 utafitiHapana

0.94

to

0.61

 vVar

0.60

ItemLayout

0.53

to

0.52

########.

0.52

ToAction

0.52

ArgsConstructor

0.51

ībā

0.50

Clik

0.49

Activations Density 0.435%

references to temporal concepts and life events

No Comments

No Known Activations