INDEX

Explanations

references to the verb "be" in various forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

іга

-0.60

ANCIA

-0.60

 Maharaja

-0.58

pertino

-0.58

hoda

-0.56

CPC

-0.56

olella

-0.56

 ergeben

-0.55

gac

-0.54

Mapa

-0.54

POSITIVE LOGITS

 youre

0.99

re

0.94

 gonna

0.92

 theyre

0.92

Lähteet

0.92

 XCTest

0.88

ScopeManager

0.86

SuppressLint

0.78

 GONNA

0.78

ropractic

0.77

Activations Density 0.065%

references to the verb "be" in various forms

No Comments

No Known Activations