INDEX

Explanations

references to football clubs and players

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 intime

-0.45

 windshield

-0.44

 sternum

-0.43

ิ้น

-0.42

tréal

-0.42

 husband

-0.41

Empire

-0.41

 elett

-0.41

SuppressLint

-0.40

 sumpay

-0.40

POSITIVE LOGITS

 youth

1.16

 junior

1.11

 Youth

1.04

junior

1.00

 juniors

0.99

youth

0.98

Youth

0.95

 Junior

0.94

 juvenil

0.89

Junior

0.88

Activations Density 0.151%

references to football clubs and players

No Comments

No Known Activations