INDEX

Explanations

names of specific locations or geographic entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ⓧ

-0.57

Datuak

-0.52

AlterField

-0.52

 ExecuteAsync

-0.50

 impact

-0.49

 coming

-0.47

writerow

-0.45

 impacts

-0.45

joda

-0.44

Blank

-0.44

POSITIVE LOGITS

yssey

0.57

허

0.56

 podjela

0.56

 initComponents

0.55

 Apothe

0.53

:{

0.52

̈

0.52

rily

0.52

)$\\

0.51

Activations Density 0.066%

names of specific locations or geographic entities

No Comments

No Known Activations