INDEX

Explanations

words related to the initiation of actions or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

NewGuid

-0.52

NullCheck

-0.51

Callum

-0.50

balanceOf

-0.50

resizingMask

-0.50

NSData

-0.48

 McRae

-0.47

WebElementEntity

-0.46

owice

-0.46

énario

-0.46

POSITIVE LOGITS

 begun

1.47

 begins

1.42

 begin

1.39

 starts

1.37

 began

1.35

 started

1.35

began

1.32

 Begin

1.31

started

1.27

 Begins

1.27

Activations Density 0.320%

words related to the initiation of actions or processes

No Comments

No Known Activations