INDEX

Explanations

discussions related to political philosophies and ideologies

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

 оригіналу

-0.53

FOOTNOTES

-0.53

GLOBALS

-0.53

writeFieldEnd

-0.52

 ComVisible

-0.52

 تضيفلها

-0.51

Manbalar

-0.51

↵↵↵

-0.51

***********

-0.49

POSITIVE LOGITS

moiselle

0.78

rrggbb

0.70

 Molière

0.67

 thereupon

0.64

 joaat

0.64

GeneratedMessage

0.64

 '\\;'

0.64

 Shakspeare

0.63

FailureListener

0.62

 Monfieur

0.61

Activations Density 2.237%

discussions related to political philosophies and ideologies

No Comments

No Known Activations