INDEX

Explanations

references to relationships and connections between people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

gypten

-0.49

ulant

-0.48

 receipts

-0.46

Utf

-0.46

 coûte

-0.45

SOLVED

-0.45

 dummies

-0.45

 utilisant

-0.45

 defiant

-0.44

kében

-0.44

POSITIVE LOGITS

 acquaintance

1.21

met

1.10

 acquaintances

1.06

 meeting

1.06

 kenal

1.01

Meeting

1.00

 introductions

0.99

 introduced

0.98

 meet

0.97

 познакоми

0.95

Activations Density 0.286%

references to relationships and connections between people

No Comments

No Known Activations