INDEX

Explanations

terms related to correct answers and evaluative responses in a structured format

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

Code assignments or equations

np_acts-logits-general · gemini-2.0-flash

assignment or equality

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

 Савезне

-0.74

TemporalType

-0.66

_('

-0.66

<caption>

-0.64

$_['

-0.63

_("

-0.59

 "..\..\

-0.59

 faſt

-0.59

RUnlock

-0.58

")(

-0.57

POSITIVE LOGITS

1.27

is

0.97

0.86

là

0.69

was

0.69

==

0.64

$=$

0.64

 adalah

0.63

$=

0.63

:=

0.62

Activations Density 0.352%

terms related to correct answers and evaluative responses in a structured format

Code assignments or equations

assignment or equality

No Comments

No Known Activations