INDEX

Explanations

specific technical jargon or terms related to structured data or programming

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

similarity or commonality

np_acts-logits-general · gemini-2.0-flash

examples and comparison

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

matchCondition

-0.76

WebElementEntity

-0.76

 ModelExpression

-0.70

principalColumn

-0.68

 ostavi

-0.68

 pouvoirs

-0.60

+:+

-0.58

 financières

-0.58

Fordítás

-0.56

 autorités

-0.56

POSITIVE LOGITS

 respectively

1.24

respectively

1.09

 respectivamente

1.00

etc

0.92

 these

0.88

etc

0.86

 alike

0.81

いずれ

0.80

 These

0.78

 examples

0.76

Activations Density 0.606%

specific technical jargon or terms related to structured data or programming

similarity or commonality

examples and comparison

No Comments

No Known Activations