INDEX

Explanations

the beginning of a new statement or paragraph

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

glLoadIdentity

-0.83

 ſta

-0.67

AndroidJUnit

-0.66

 Mahomet

-0.66

Hentet

-0.66

Бахар

-0.65

 Reſ

-0.64

 bershka

-0.63

 doubtnut

-0.63

 ſche

-0.62

POSITIVE LOGITS

findpost

0.55

kannya

0.50

 spesies

0.50

 referenties

0.49

 actionMode

0.48

Sp

0.48

mesg

0.47

 ProtoMessage

0.46

↵↵

0.45

]")]

0.45

Activations Density 0.009%

the beginning of a new statement or paragraph

No Comments

No Known Activations