INDEX

Explanations

markup elements and comments in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

-1.46

 للمعارف

-0.74

</

-0.73

twimg

-0.67

WithIdentifier

-0.67

withIdentifier

-0.60

Clik

-0.59

-0.58

mybatisplus

-0.57

\\

-0.57

POSITIVE LOGITS

colnshire

0.47

rambled

0.46

 Porque

0.45

 klä

0.45

*</

0.44

$',

0.44

iniums

0.44

"`

0.44

üksek

0.43

 gründ

0.43

Activations Density 0.232%

markup elements and comments in code

No Comments

No Known Activations

markup elements and comments in code

No Comments

No Known Activations