INDEX

Explanations

phrases indicating potential opportunities or outcomes related to acceptance and conditions in a formal context

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

future tense indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

OGND

-0.64

下载附件

-0.59

extAlignment

-0.56

 nakalista

-0.53

 BoxFit

-0.52

RectangleBorder

-0.52

ChildScrollView

-0.51

IContainer

-0.50

AddTagHelper

-0.50

+#+

-0.50

POSITIVE LOGITS

 nantinya

0.38

 will

0.35

nextProps

0.35

 nanti

0.34

将会

0.34

 akan

0.33

 dovrà

0.32

 potrà

0.31

 vectorielle

0.31

assertAll

0.30

Activations Density 0.070%

phrases indicating potential opportunities or outcomes related to acceptance and conditions in a formal context

future tense indicators

No Comments

No Known Activations