INDEX

Explanations

positive and negative evaluations or ratings

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

code blocks and data tables

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

↵↵

-0.59

in

-0.56

and

-0.49

the

-0.49

 under

-0.48

or

-0.46

 model

-0.46

 defin

-0.46

cal

-0.46

POSITIVE LOGITS

MigrationBuilder

1.25

+#+#

1.13

 ExecuteAsync

1.03

AndEndTag

1.00

tvguidetime

0.99

StoryboardSegue

0.99

IntoConstraints

0.96

MessageTagHelper

0.96

expandindo

0.95

 Roskov

0.93

Activations Density 0.089%

positive and negative evaluations or ratings

code blocks and data tables

No Comments

No Known Activations