INDEX

Explanations

characters, particularly named individuals in a narrative context

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

InputBorder

-0.80

bootstrapcdn

-0.70

]")]

-0.67

 pinulongan

-0.65

IntoConstraints

-0.63

jstor

-0.62

aarrggbb

-0.61

 kubwa

-0.61

arrol

-0.60

MessageOf

-0.59

POSITIVE LOGITS

 виправивши

0.55

 oprot

0.51

Kanpo

0.46

beforeEach

0.46

SuspendLayout

0.44

bewerken

0.43

 Wikimedijinoj

0.43

AddAttribute

0.42

 đương

0.42

 poche

0.42

Activations Density 0.132%

characters, particularly named individuals in a narrative context

No Comments

No Known Activations