INDEX

Explanations

the occurrence of the word "an" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 mostrarán

-0.61

日閲覧

-0.61

ResponseWriter

-0.60

 kaarangay

-0.59

AccessorTable

-0.58

acaktır

-0.57

 pinulongan

-0.56

 فريبيس

-0.54

ynx

-0.54

imenti

-0.53

POSITIVE LOGITS

an

2.13

AN

1.27

ane

1.22

annya

1.16

ans

1.14

anes

1.13

ان

1.07

anos

1.07

aned

1.06

anas

1.04

Activations Density 0.080%

the occurrence of the word "an" in various contexts

No Comments

No Known Activations