INDEX

Explanations

mentions of character encodings, specifically UTF

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

utf-8 encoding

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

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

writeFieldEnd

-0.71

ябре

-0.64

providedIn

-0.61

évaluateur

-0.61

__(/*!

-0.59

jenigen

-0.59

homonymie

-0.58

IBAction

-0.57

principalColumn

-0.57

sizeCache

-0.57

POSITIVE LOGITS

utf

1.49

utf

1.24

UTF

1.20

UTF

1.15

Utf

1.11

Utf

0.79

StandardCharsets

0.50

uint

0.46

ChildScrollView

0.44

csrf

0.42

Activations Density 0.002%

mentions of character encodings, specifically UTF

utf-8 encoding

No Comments

No Known Activations