INDEX

Explanations

punctuation and author attribution within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

cheiben

-0.51

〒

-0.49

atória

-0.49

 orizz

-0.48

Біографія

-0.47

 courrier

-0.46

ждую

-0.46

 specchio

-0.46

piecze

-0.45

Distribuzione

-0.45

POSITIVE LOGITS

jsonwebtoken

0.75

onomía

0.67

 nahilalakip

0.62

Lähteet

0.61

 heapq

0.61

WithIOException

0.60

]<<

0.57

PrototypeOf

0.57

 <<<<<<<<<<<<<<

0.57

jme

0.56

Activations Density 0.116%

punctuation and author attribution within the text

No Comments

No Known Activations