INDEX

Explanations

words related to processes, conditions, and states that indicate progress or improvement

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

Text following questions marked by "Q:"

np_acts-logits-general · gemini-2.0-flash

technical descriptions and specifications

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 تضيفلها

-0.84

Personendaten

-0.72

räck

-0.69

MigrationBuilder

-0.68

"]="

-0.67

 galore

-0.62

DockStyle

-0.61

__":

-0.60

 defaultstate

-0.60

 quoque

-0.58

POSITIVE LOGITS

WebServlet

0.54

ródło

0.50

ViewImports

0.50

 насељу

0.49

HasAnnotation

0.49

saraba

0.48

 when

0.48

 recommandée

0.48

aktery

0.47

 للغاية

0.47

Activations Density 0.758%

words related to processes, conditions, and states that indicate progress or improvement

Text following questions marked by "Q:"

technical descriptions and specifications

No Comments

No Known Activations