INDEX

Explanations

the word "Well" and variations of it to indicate affirmations or transitions in conversation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 Roskov

-1.04

OGND

-0.84

Personensuche

-0.84

IsContent

-0.82

WebElementEntity

-0.76

 betweenstory

-0.73

DockStyle

-0.72

 للاسماء

-0.70

fbox

-0.69

PullParser

-0.68

POSITIVE LOGITS

 Well

0.85

Well

0.77

 well

0.64

 technically

0.60

 some

0.57

Welp

0.54

if

0.53

you

0.52

 since

0.51

well

0.50

Activations Density 0.067%

the word "Well" and variations of it to indicate affirmations or transitions in conversation

No Comments

No Known Activations