INDEX

Explanations

linguistic elements related to definite articles in various languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 myſelf

-1.12

 itſelf

-1.10

 Houſe

-1.07

 raiſ

-1.06

 Monfieur

-1.05

 houſe

-1.04

 themſelves

-1.01

 Shaksp

-0.99

 becauſe

-0.97

 ſche

-0.97

POSITIVE LOGITS

the

1.17

la

1.02

le

0.96

The

0.95

La

0.93

THE

0.90

 final

0.90

 entire

0.89

sa

0.85

Le

0.85

Activations Density 0.022%

linguistic elements related to definite articles in various languages

No Comments

No Known Activations