INDEX

Explanations

the word "con" and its variations, often in the context of legal or scientific terminology

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

enumi

-0.67

inafter

-0.65

nonatomic

-0.63

 CreateTagHelper

-0.60

tvguidetime

-0.60

Reprodução

-0.55

letal

-0.55

 naturalistic

-0.53

ISTICS

-0.53

 Nossa

-0.53

POSITIVE LOGITS

 autorytatywna

0.48

 Edison

0.47

 Nast

0.47

 Paper

0.45

 ISNI

0.45

 brio

0.44

 кӀ

0.44

Con

0.43

клопе

0.43

 trast

0.43

Activations Density 0.131%

the word "con" and its variations, often in the context of legal or scientific terminology

No Comments

No Known Activations