INDEX

Explanations

terms related to emotional and mental states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 الرياضيه

-0.97

 betweenstory

-0.90

Personensuche

-0.83

tagHelperRunner

-0.71

ConstraintMaker

-0.68

SaveVideo

-0.67

apimachinery

-0.67

IUrlHelper

-0.67

AutoScaleMode

-0.66

 мәкал

-0.66

POSITIVE LOGITS

 mode

0.92

 version

0.90

 category

0.68

 maupun

0.61

 counterpart

0.60

 side

0.59

 level

0.59

ほう

0.59

 Mode

0.59

or

0.58

Activations Density 1.815%

terms related to emotional and mental states

No Comments

No Known Activations