INDEX

Explanations

terms related to horses and equine activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

czaj

-0.77

Utf

-0.65

 Cancun

-0.63

kheim

-0.63

Nef

-0.61

 שול

-0.61

tagHelperRunner

-0.61

 jadx

-0.59

 Cheesecake

-0.59

cadilly

-0.58

POSITIVE LOGITS

 horse

2.31

 horses

2.27

 Horse

2.14

 Horses

2.12

Horse

2.11

 HORSE

2.01

horse

2.00

horses

1.89

Horses

1.86

 equine

1.65

Activations Density 0.068%

terms related to horses and equine activities

No Comments

No Known Activations