INDEX

Explanations

details related to personal and professional backgrounds

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 nonatomic

-0.67

原始内容存档于

-0.50

 membutuhkan

-0.48

الحياه

-0.47

 potrze

-0.45

 EClass

-0.43

ngrx

-0.43

qrstuvwxyz

-0.42

 demor

-0.42

gye

-0.42

POSITIVE LOGITS

 served

1.20

 serve

1.11

 chaired

1.09

 serves

1.01

served

1.00

 serving

1.00

 authored

0.98

 worked

0.97

 Serve

0.97

serve

0.96

Activations Density 0.487%

details related to personal and professional backgrounds

No Comments

No Known Activations