INDEX

Explanations

elements related to programming, specifically in data handling and manipulation

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

Code or configuration snippets containing specific keywords

np_acts-logits-general · gemini-2.0-flash

dLMLifecyclePolicy or archaic spelling

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

-0.63

erapeutic

-0.62

-0.58

der

-0.58

ividual

-0.56

ab

-0.55

var

-0.54

je

-0.54

sur

-0.53

POSITIVE LOGITS

ſelves

1.15

 myſelf

1.07

Efq

1.05

 Reſ

1.05

 ſever

1.05

 uſe

1.05

 itſelf

1.04

 uſed

1.03

 purpoſe

1.02

 reaſon

1.01

Activations Density 0.521%

elements related to programming, specifically in data handling and manipulation

Code or configuration snippets containing specific keywords

dLMLifecyclePolicy or archaic spelling

No Comments

No Known Activations