INDEX

Explanations

questions and elements of inquiry

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

 nuanced

-0.59

 leveraging

-0.57

 backstory

-0.54

—

-0.52

—

-0.52

 Visual

-0.52

Anyways

-0.52

 blin

-0.52

cipar

-0.52

POSITIVE LOGITS

 inconvénients

0.72

 symboles

0.69

 célé

0.67

setVerticalGroup

0.67

లాలు

0.66

antaranya

0.65

 muß

0.62

 quelquefois

0.62

 idéia

0.61

 meestal

0.61

Activations Density 0.314%

questions and elements of inquiry

No Comments

No Known Activations