INDEX

Explanations

expressions of apology and SQL commands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 bezeichneter

-0.82

 itſelf

-0.68

 ―――――

-0.67

Efq

-0.66

 moschino

-0.66

 Monfieur

-0.65

 CreateTagHelper

-0.65

 ſever

-0.65

 gawas

-0.63

 ویکی‌پدیای

-0.63

POSITIVE LOGITS

 please

1.18

please

1.08

 Please

0.98

Please

0.94

请

0.93

 PLEASE

0.92

PLEASE

0.84

請

0.82

 pleases

0.82

 apologize

0.81

Activations Density 0.095%

expressions of apology and SQL commands

No Comments

No Known Activations