INDEX

Explanations

occurrences of the term "pos" in various contexts

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

pos (positive/position)

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

 CreateTagHelper

-0.49

queryInterface

-0.48

randomUUID

-0.48

 deleteById

-0.47

ChildScrollView

-0.46

runApp

-0.45

 CommonModule

-0.45

ChrTalk

-0.44

RTGC

-0.43

 createContext

-0.43

POSITIVE LOGITS

pos

2.19

Pos

1.55

Pos

1.24

POS

1.03

 post

0.89

 posa

0.88

setPos

0.84

 poss

0.82

POS

0.80

pos

0.78

Activations Density 0.003%

occurrences of the term "pos" in various contexts

pos (positive/position)

No Comments

No Known Activations