INDEX

Explanations

sequences of numerical values or identifiers in a structured format

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

LookAnd

-1.50

 itſelf

-1.42

 myſelf

-1.33

 themſelves

-1.31

 uſed

-1.30

 purpoſe

-1.28

 Roskov

-1.26

AsUp

-1.26

 pleaſure

-1.22

 ―――――

-1.21

POSITIVE LOGITS

0.80

0.73

“

0.72

$\

0.71

<strong>

0.68

the

0.67

his

0.66

0.65

<b>

0.65

Activations Density 0.254%

sequences of numerical values or identifiers in a structured format

No Comments

No Known Activations