INDEX

Explanations

sections or formatting markers in structured documents such as code or scientific papers

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

↵

-0.54

-0.47

↵↵

-0.45

 plata

-0.41

En

-0.39

-0.38

<eos>

-0.37

↵↵↵

-0.37

-0.36

-0.35

POSITIVE LOGITS

 JpaRepository

0.87

 disambiguazione

0.84

 متعلقه

0.84

তথ্যসূত্র

0.83

ThroughAttribute

0.83

RectangleBorder

0.82

 vectorielle

0.81

 vPvB

0.81

 BorderRadius

0.80

 BoxFit

0.80

Activations Density 0.311%

sections or formatting markers in structured documents such as code or scientific papers

No Comments

No Known Activations