INDEX

Explanations

terms related to administrative processes and procedures

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

the word "Administrative" in formal legal and procedural contexts.

oai_token-act-pair · claude-4-5-haiku Triggered by @emiglarou

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

featureID

-0.60

LEncoder

-0.52

ztály

-0.52

Chip

-0.47

TagMode

-0.47

uride

-0.46

chip

-0.45

 Woody

-0.45

 faſt

-0.45

HasForeignKey

-0.44

POSITIVE LOGITS

stration

0.56

strator

0.54

errHandler

0.50

ISTRATION

0.49

istered

0.47

 Admin

0.46

 admin

0.43

administ

0.42

Admin

0.41

ister

0.41

Activations Density 0.128%

terms related to administrative processes and procedures

the word "Administrative" in formal legal and procedural contexts.

No Comments

No Known Activations