INDEX

Explanations

instances of questioning or uncertainty in conversations

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

Japanese punctuation 。

np_acts-logits-general · gemini-2.0-flash

tag helper compilation

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

-0.43

is

-0.42

<unused61>

-0.41

<unused62>

-0.41

as

-0.41

<unused63>

-0.40

 make

-0.38

ial

-0.38

POSITIVE LOGITS

 CreateTagHelper

1.16

 mergeFrom

1.14

ImageContext

1.11

RegressionTest

1.09



1.07

parsedMessage

1.07

AndEndTag

1.07

 &___

1.06

SequentialGroup

1.06

tagHelperRunner

1.04

Activations Density 0.177%

instances of questioning or uncertainty in conversations

Japanese punctuation 。

tag helper compilation

No Comments

No Known Activations