INDEX

Explanations

specific geographic locations and proper nouns associated with places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

MessageOf

-0.65

 jScrollPane

-0.60

ãy

-0.58

اضي

-0.49

printStackTrace

-0.46

ofold

-0.46

',

-0.45

 useState

-0.45

 CreateTagHelper

-0.44

 presente

-0.44

POSITIVE LOGITS

umburg

0.69

 suburb

0.67

 Altos

0.64

 Carlsbad

0.62

ⓧ

0.62

mitos

0.62

ดุ

0.60

 Torrance

0.59

 suburbs

0.59

Plano

0.58

Activations Density 0.992%

specific geographic locations and proper nouns associated with places

No Comments

No Known Activations