INDEX

Explanations

terms related to focus and concentration on specific subjects or projects

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

 disposent

-0.57

zine

-0.56

 paik

-0.54

 thereof

-0.52

 rând

-0.52

-0.50

 sähkö

-0.50

 Appleton

-0.50

-0.49

ny

-0.48

POSITIVE LOGITS

 nahilalakip

1.10

 pinulongan

0.98

]")]

0.95

oa̍t

0.92

 betweenstory

0.90

verifyException

0.87

Autoritní

0.87

@[+][

0.87

SourceChecksum

0.83

octanol

0.81

Activations Density 0.174%

terms related to focus and concentration on specific subjects or projects

No Comments

No Known Activations