INDEX

Explanations

occurrences of the word "start" and related terms in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

ONYMOUS

-0.72

 LCCN

-0.68

führ

-0.65

 Wolken

-0.65

er

-0.63

 objs

-0.63

;'>

-0.63

zeitung

-0.62

asserole

-0.62

jö

-0.62

POSITIVE LOGITS

getStart

1.10

START

1.06

 getStart

1.02

Start

1.00

start

0.98

 START

0.98

 Start

0.95

 onStart

0.83

 start

0.83

 Starts

0.80

Activations Density 0.102%

occurrences of the word "start" and related terms in various contexts

No Comments

No Known Activations