INDEX

Explanations

concepts related to definitions and classifications

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

Following "is"

np_acts-logits-general · gemini-2.0-flash

is equivalent or similar

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

Portale

-0.64

IndentedString

-0.53

WebElementEntity

-0.48

 nakalista

-0.48

 saisi

-0.47

لمة

-0.43

seende

-0.42

 jspb

-0.41

Portail

-0.41

 kesulitan

-0.41

POSITIVE LOGITS

 adopted

0.80

extAlignment

0.78

PerformLayout

0.77

adopted

0.76

 applied

0.72

 itſelf

0.71

 valid

0.68

 صوتيه

0.68

 echoed

0.67

 corroborated

0.65

Activations Density 0.816%

concepts related to definitions and classifications

Following "is"

is equivalent or similar

No Comments

No Known Activations