INDEX

Explanations

legal terminology and concepts related to rules and application

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

terase

-0.58

Hentet

-0.53

IZON

-0.50

★★★★☆

-0.49

NOPQRST

-0.49

 quitté

-0.48

 resourceCulture

-0.47

 rhestr

-0.45

edos

-0.45

████

-0.45

POSITIVE LOGITS

 apply

2.90

 applies

2.90

apply

2.46

 Apply

2.44

 Applies

2.35

Apply

2.30

 applied

2.28

 applying

2.20

 APPLY

2.19

 Applying

2.04

Activations Density 0.901%

legal terminology and concepts related to rules and application

No Known Activations