INDEX

Explanations

formatting or structural elements typically found in programming or licensing language

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

"AS IS" BASIS and table formatting

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 OnTrigger

-0.54

 Affleck

-0.51

 incontr

-0.50

 pade

-0.49

onavir

-0.49

 MatDialog

-0.48

VertexArray

-0.47

 Quaternion

-0.46

GTCX

-0.46

Quaternion

-0.45

POSITIVE LOGITS

lccc

1.65

lcccc

1.27

lcc

1.27

lrrr

1.17

lccccc

1.11

lrrrr

1.03

lrr

1.02

NameInMap

0.94

lcccccc

0.91

日閲覧

0.59

Activations Density 0.001%

formatting or structural elements typically found in programming or licensing language

"AS IS" BASIS and table formatting

No Comments

No Known Activations