INDEX

Explanations

terms indicating non-standard or unconventional entities or conditions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 urbanas

-0.59

 décider

-0.52

 vectorielle

-0.51

eventually

-0.50

Bref

-0.49

ToServer

-0.49

 metropolitana

-0.48

 particulière

-0.48

 culturelle

-0.48

 dentaire

-0.48

POSITIVE LOGITS

 ProtoMessage

0.92

AddTagHelper

0.89

tagHelperRunner

0.89

原始内容存档于

0.87

Билгалдахарш

0.86

non

0.84

 initComponents

0.84

 jsPsych

0.83

 виправивши

0.81

TargetException

0.80

Activations Density 0.154%

terms indicating non-standard or unconventional entities or conditions

No Comments

No Known Activations