INDEX

Explanations

references to historical or political figures

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

Followed by punctuation or a letter

np_acts-logits-general · gemini-2.0-flash

possessive noun endings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-1.02

-0.93

-0.92

↵

-0.91

in

-0.90

-0.88

-0.86

-0.83

↵↵

-0.83

POSITIVE LOGITS

 متعلقه

1.70

RenderAtEndOf

1.56

expandindo

1.52

 bezeichneter

1.42

 CreateTagHelper

1.38

 betweenstory

1.37

ValueStyle

1.35

 tartalomajánló

1.34

Efq

1.34

 الرياضيه

1.31

Activations Density 0.125%

references to historical or political figures

Followed by punctuation or a letter

possessive noun endings

No Comments

No Known Activations