INDEX

Explanations

references to purchasing and buying items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 withal

-0.64

 penal

-0.64

 Beding

-0.64

 >=",

-0.62

 disarm

-0.61

hower

-0.61

 ſtate

-0.61

rungsseite

-0.61

tvguidetime

-0.61

UserScript

-0.60

POSITIVE LOGITS

 purchase

1.15

 purchased

1.07

 bought

1.05

 buys

1.02

 purchases

1.02

buy

1.01

 purchasing

1.01

purchased

1.01

purchase

1.00

buy

0.98

Activations Density 0.192%

references to purchasing and buying items

No Comments

No Known Activations