INDEX

Explanations

terms related to golf

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

phrine

-0.58

granate

-0.49

AllowUser

-0.45

\"");

-0.44

miert

-0.42

ittens

-0.41

cency

-0.41

 Seguro

-0.41

fandom

-0.41

 henne

-0.41

POSITIVE LOGITS

 golf

1.72

golf

1.63

Golf

1.62

 Golf

1.62

 golfing

1.58

 GOLF

1.53

 golfer

1.52

 golfers

1.43

GOLF

1.40

PGA

1.09

Activations Density 0.095%

terms related to golf

No Comments

No Known Activations