INDEX

Explanations

affirmative statements and expressions of agreement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 '\\;'

-0.65

ftagPool

-0.58

bcryptjs

-0.58

ppuden

-0.56

commodations

-0.55

principalTable

-0.54

httphttps

-0.54

 كورة

-0.53

fjspx

-0.51

vacy

-0.50

POSITIVE LOGITS

esgue

0.68

 contraire

0.54

PMailer

0.53

tagHelperRunner

0.50

Referencie

0.49

linspace

0.49

izop

0.47

原始内容存档于

0.46

 Tacitus

0.46

 Pristup

0.46

Activations Density 0.487%

affirmative statements and expressions of agreement

No Comments

No Known Activations