INDEX

Explanations

terms related to verbs and actions, particularly in legal or formal contexts

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

Not in Any Lists

No Comments

Negative Logits

-0.81

-0.69

in

-0.67

-0.65

to

-0.64

-0.62

-0.61

at

-0.61

POSITIVE LOGITS

Efq

1.50

 Anſ

1.41

 pleaſure

1.40

 itſelf

1.37

 myſelf

1.35

 Majefty

1.31

ſelves

1.30

 Jefus

1.21

 purpoſe

1.20

 ―――――

1.19

Activations Density 0.056%

terms related to verbs and actions, particularly in legal or formal contexts

No Comments

No Known Activations