INDEX

Explanations

references to characters and their actions within a fictional narrative

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

llac

-0.75

 Shogun

-0.71

 متعلقه

-0.67

 ExecuteAsync

-0.66

dozer

-0.65

География

-0.61

$_['

-0.61

fastjson

-0.60

thâu

-0.59

 Linger

-0.58

POSITIVE LOGITS

 Hogwarts

1.05

 Harry

1.04

 wizard

0.99

Harry

0.95

wizard

0.93

 Dumbledore

0.93

 wizards

0.92

 harry

0.91

 Voldemort

0.89

 Potter

0.83

Activations Density 0.144%

references to characters and their actions within a fictional narrative

No Comments

No Known Activations