INDEX

Explanations

references to swimming pools and related activities

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

IUrlHelper

-0.76

IBOutlet

-0.62

neté

-0.60

 TestCase

-0.60

 "..\..\..\

-0.58

Hentet

-0.58

 متعلقه

-0.57

Kanpo

-0.56

hyrchwyd

-0.56

 veze

-0.54

POSITIVE LOGITS

 pools

1.24

 pool

1.20

 Pool

1.17

 POOL

1.15

pools

1.13

 Pools

1.12

pool

1.06

Pools

1.03

Pool

0.99

POOL

0.93

Activations Density 0.093%

references to swimming pools and related activities

No Comments

No Known Activations