INDEX

Explanations

statements related to expectations in coding tests

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Ribera

-0.76

 Lombar

-0.69

 Medellín

-0.68

mallows

-0.65

 Frédéric

-0.61

 accelerators

-0.61

PSM

-0.60

ednes

-0.59

ۜ

-0.58

encers

-0.57

POSITIVE LOGITS

]-->

0.67

 estimés

0.66

 فريبيس

0.65

abstractmethod

0.65

 StatefulWidget

0.63

setattr

0.61

 otomatig

0.59

 ArrayAdapter

0.59

DriverManager

0.59

DBNull

0.59

Activations Density 0.012%

statements related to expectations in coding tests

No Comments

No Known Activations