INDEX

Explanations

numerical values and their relationships within a programming context

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 queſta

-0.78

 незавершена

-0.70

aarrggbb

-0.70

 linkovi

-0.65

хьтан

-0.64

 CreateTagHelper

-0.63

 &___

-0.63

 ویکی‌پدی

-0.62

 utafitiHapana

-0.61

awtextra

-0.57

POSITIVE LOGITS

 виправивши

0.39

 منها

0.35

又是

0.35

 yine

0.35

 ditto

0.34

eamiento

0.33

 dehors

0.32

 again

0.31

 makro

0.31

Activations Density 0.002%

numerical values and their relationships within a programming context

No Comments

No Known Activations