INDEX

Explanations

phrases indicating difficulty in writing or expressing thoughts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

ImageContext

-0.62

principalColumn

-0.55

HtmlAttribute

-0.55

oredCriteria

-0.54

DeleteBehavior

-0.50

RegressionTest

-0.48

MessageState

-0.47

참고

-0.46

SBATCH

-0.45

原始内容存档于

-0.45

POSITIVE LOGITS

+/**

0.41

 argint

0.40

ategorised

0.40

 Turch

0.37

 vastaan

0.37

 marke

0.36

 sepen

0.36

">//

0.36

 pember

0.35

 muhte

0.35

Activations Density 0.000%

phrases indicating difficulty in writing or expressing thoughts

No Comments

No Known Activations