INDEX

Explanations

phrases indicating citations or prior indications of truth or fact

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

introducing a point or observation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Sal

-0.37

jinal

-0.36

영

-0.35

Mat

-0.35

Os

-0.35

<h1>

-0.35

Sal

-0.34

Je

-0.33

Je

-0.33

POSITIVE LOGITS

expandindo

0.83

 okuyayım

0.66

bewerken

0.66

IndentedString

0.65

 AssemblyCompany

0.63

ंदीखरीदारी

0.62

 '\\;'

0.62

 disambiguazione

0.60

 ainfi

0.60

 CreateTagHelper

0.60

Activations Density 0.046%

phrases indicating citations or prior indications of truth or fact

introducing a point or observation

No Comments

No Known Activations