INDEX

Explanations

references to characters and their attributes in a narrative or gaming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

fjspx

-0.85

webElementXpaths

-0.75

onViewCreated

-0.67

NameInMap

-0.67

ngdoc

-0.65

 المعيارى

-0.64

 disambiguazione

-0.64

/\.

-0.63

@[+][

-0.63

principalTable

-0.63

POSITIVE LOGITS

 tiras

0.49

Cal

0.44

 Mortuary

0.44

ಳ

0.44

 infiltrate

0.43

 Enforcement

0.43

Sep

0.42

 skak

0.42

sama

0.41

Activations Density 0.306%

references to characters and their attributes in a narrative or gaming context

No Comments

No Known Activations