INDEX

Explanations

programming-related terms and structures, particularly those associated with encoding, decoding, and data handling

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

principalColumn

-0.82

 صوتيه

-0.58

 intptr

-0.57

Personendaten

-0.56

 Италијани

-0.54

 kasarigan

-0.52

awtextra

-0.51

GOTREF

-0.51

providedIn

-0.51

EndContext

-0.50

POSITIVE LOGITS

 structure

0.52

 impression

0.49

 addition

0.47

EUROPA

0.46

 Structure

0.46

 helper

0.45

 storage

0.45

 campaign

0.45

 institution

0.45

 development

0.44

Activations Density 0.027%

programming-related terms and structures, particularly those associated with encoding, decoding, and data handling

No Comments

No Known Activations