INDEX

Explanations

instances of the word "would" indicating conditional or hypothetical statements

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

Tokens following "would"

np_acts-logits-general · gemini-2.0-flash

habitual recurrence

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.48

 ampliación

-0.45

↵↵

-0.43

cephala

-0.42

 είναι

-0.41

createCell

-0.39

ступить

-0.39

 estren

-0.39

 General

-0.38

POSITIVE LOGITS

 فريبيس

1.12

RenderAtEndOf

0.91

 esternos

0.91

 betweenstory

0.84

 дописавши

0.83

MethodManager

0.82

المناصب

0.82

AutoScaleMode

0.82

 Савезне

0.82

 periodically

0.81

Activations Density 0.102%

instances of the word "would" indicating conditional or hypothetical statements

Tokens following "would"

habitual recurrence

No Comments

No Known Activations