INDEX

Explanations

terms related to manipulation and control

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 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

elemField

-0.52

Rohy

-0.50

ChildScrollView

-0.50

oredCriteria

-0.47

CrossRef

-0.47

IndentedString

-0.46

 onResponse

-0.46

 Autorizaciones

-0.46

ngths

-0.45

UIFont

-0.43

POSITIVE LOGITS

 manipulation

1.20

 Manipulation

1.20

 manipulate

1.12

manip

1.10

 Manip

1.09

 manip

1.05

 manipulated

1.05

 manipulations

1.05

Manip

1.02

Manipulation

1.00

Activations Density 0.069%

terms related to manipulation and control

No Comments

No Known Activations