INDEX

Explanations

references to technical specifications and standards

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

Text after a punctuation mark

np_acts-logits-general · gemini-2.0-flash

EdittestAIfTheSam*Is

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

՚

-1.29

)");

-1.19

"):

-1.06

出版年

-1.01

.")

-1.00

.",

-0.99

!")

-0.97

.");

-0.95

?」

-0.94

.";

-0.94

POSITIVE LOGITS

2.59

2.15

1.68

1.64

1.59

1.57

1.55

1.50

Activations Density 0.336%

references to technical specifications and standards

Text after a punctuation mark

EdittestAIfTheSam*Is

No Comments

No Known Activations